Search Results for author:
Found 208 papers, 88 papers with code
Federated Learning with Only Positive Labels by Exploring Label Correlations
Specifically, FedALC estimates the label correlations in the class embedding learning for different label pairs and utilizes it to improve the model training.
Continuous Spiking Graph Neural Networks
Inspired by recent spiking neural networks (SNNs), which emulate a biological inference process and provide an energy-efficient neural architecture, we incorporate the SNNs with CGNNs in a unified framework, named Continuous Spiking Graph Neural Networks (COS-GNN).
Heterogeneous Federated Learning with Splited Language Model
Federated Split Learning (FSL) is a promising distributed learning paradigm in practice, which gathers the strengths of both Federated Learning (FL) and Split Learning (SL) paradigms, to ensure model privacy while diminishing the resource overhead of each client, especially on large transformer models in a resource-constrained environment, e. g., Internet of Things (IoT).
Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning
In this work, we design a two-stage fine-tuning algorithm to improve the instruction-following ability (especially the translation direction) of LLMs.
A Unified and General Framework for Continual Learning
Extensive experiments on CL benchmarks and theoretical analysis demonstrate the effectiveness of the proposed refresh learning.
Communication-Efficient Distributed Learning with Local Immediate Error Compensation
However, existing compression methods either perform only unidirectional compression in one iteration with higher communication cost, or bidirectional compression with slower convergence rate.
Revisiting Knowledge Distillation for Autoregressive Language Models
Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model.
Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping
To further exploit the capabilities of bootstrapping, we investigate and adjust the training order of data, which yields improved performance of the model.
Representation Surgery for Multi-Task Model Merging
That is, there is a significant discrepancy in the representation distribution between the merged and individual models, resulting in poor performance of merged MTL.
Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
A notable challenge is mitigating the interference between parameters of different models, which can substantially deteriorate performance.
Multimodal Neurodegenerative Disease Subtyping Explained by ChatGPT
Thus, we propose a multimodal framework that uses early-stage indicators such as imaging, genetics and clinical assessments to classify AD patients into subtypes at early stages.
Solving Continual Offline Reinforcement Learning with Decision Transformer
We aim to investigate whether Decision Transformer (DT), another offline RL paradigm, can serve as a more suitable offline continuous learner to address these issues.
WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge
Sentiment analysis is rapidly advancing by utilizing various data modalities (e. g., text, image).
OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models
Advancing automated programming necessitates robust and comprehensive code generation benchmarks, yet current evaluation frameworks largely neglect object-oriented programming (OOP) in favor of functional programming (FP), e. g., HumanEval and MBPP.
Siamese Networks with Soft Labels for Unsupervised Lesion Detection and Patch Pretraining on Screening Mammograms
Self-supervised learning has become a popular way to pretrain a deep learning model and then transfer it to perform downstream tasks.
Neural Network Approximation for Pessimistic Offline Reinforcement Learning
In this paper, we establish a non-asymptotic estimation error of pessimistic offline RL using general neural network approximation with $\mathcal{C}$-mixing data regarding the structure of networks, the dimension of datasets, and the concentrability of data coverage, under mild assumptions.
Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion
At the upper level, we focus on learning a shared Concrete mask to identify the subspace, while at the inner level, model merging is performed to maximize the performance of the merged model.
Take an Irregular Route: Enhance the Decoder of Time-Series Forecasting Transformer
With the development of Internet of Things (IoT) systems, precise long-term forecasting method is requisite for decision makers to evaluate current statuses and formulate future policies.
Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld
While large language models (LLMs) excel in a simulated world of texts, they struggle to interact with the more realistic world without perceptions of other modalities such as visual or audio signals.
Task-Distributionally Robust Data-Free Meta-Learning
TDS leads to a biased meta-learner because of the skewed task distribution towards newly generated tasks.
Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization
By fully exploring both variant and invariant parameters, our EVIL can effectively identify a robust subnetwork to improve OOD generalization.
FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning
Therefore, the label guidance on labeled data is hard to be propagated to unlabeled data.
Modeling Path Importance for Effective Alzheimer's Disease Drug Repurposing
Thus, leveraging learned embeddings allows MPI to effectively differentiate the importance among paths.
Rethinking SIGN Training: Provable Nonconvex Acceleration without First- and Second-Order Gradient Lipschitz
Sign-based stochastic methods have gained attention due to their ability to achieve robust performance despite using only the sign information for parameter updates.
Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models
The key algorithm in solving ZSAQ is the SAM-SGA optimization, which aims to improve the quantization accuracy and model generalization via optimizing a minimax problem.
Enhancing Column Generation by Reinforcement Learning-Based Hyper-Heuristic for Vehicle Routing and Scheduling Problems
In addition, we specify RLHH to solve two typical combinatorial optimization problems: Vehicle Routing Problem with Time Windows (VRPTW) and Bus Driver Scheduling Problem (BDSP).
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
Although a sparse Mixture of Experts (MoE) can reduce the cost by activating a small subset of parameters (e. g., one expert) for each input, its computation escalates significantly if increasing the number of activated experts, limiting its practical utility.
Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer
The Mixture of Experts (MoE) has emerged as a highly successful technique in deep learning, based on the principle of divide-and-conquer to maximize model capacity without significant additional computational cost.
Learn From Model Beyond Fine-Tuning: A Survey
LFM focuses on the research, modification, and design of FM based on the model interface, so as to better understand the model structure and weights (in a black box environment), and to generalize the model to downstream tasks.
Debias the Training of Diffusion Models
Diffusion models have demonstrated compelling generation quality by optimizing the variational lower bound through a simple denoising score matching loss.
ChatGPT for Computational Topology
This work serves as an initial step towards effectively transforming pure mathematical theories into practical computational tools, with the ultimate goal of enabling real applications across diverse fields.
Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL).
DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning
Constrained policy search (CPS) is a fundamental problem in offline reinforcement learning, which is generally solved by advantage weighted regression (AWR).
Asymmetrically Decentralized Federated Learning
To further improve algorithm performance and alleviate local heterogeneous overfitting in Federated Learning (FL), our algorithm combines the Sharpness Aware Minimization (SAM) optimizer and local momentum.
Parameter Efficient Multi-task Model Fusion with Partial Linearization
We demonstrate that our partial linearization technique enables a more effective fusion of multiple tasks into a single model, outperforming standard adapter tuning and task arithmetic alone.
Which mode is better for federated learning? Centralized or Decentralized
Both centralized and decentralized approaches have shown excellent performance and great application value in federated learning (FL).
Efficient Federated Prompt Tuning for Black-box Large Pre-trained Models
With the blowout development of pre-trained models (PTMs), the efficient tuning of these models for diverse downstream applications has emerged as a pivotal research concern.
AdaMerging: Adaptive Model Merging for Multi-Task Learning
This approach aims to autonomously learn the coefficients for model merging, either in a task-wise or layer-wise manner, without relying on the original training data.
Towards Stable Backdoor Purification through Feature Shift Tuning
Our analysis shows that with the low poisoning rate, the entanglement between backdoor and clean features undermines the effect of tuning-based defenses.
Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation
Zero-shot translation (ZST), which is generally based on a multilingual neural machine translation model, aims to translate between unseen language pairs in training data.
Deep Model Fusion: A Survey
Specifically, we categorize existing deep model fusion methods as four-fold: (1) "Mode connectivity", which connects the solutions in weight space via a path of non-increasing loss, in order to obtain better initialization for model fusion; (2) "Alignment" matches units between neural networks to create better conditions for fusion; (3) "Weight average", a classical model fusion method, averages the weights of multiple models to obtain more accurate results closer to the optimal solution; (4) "Ensemble learning" combines the outputs of diverse models, which is a foundational technique for improving the accuracy and robustness of the final model.
Are Large Language Models Really Robust to Word-Level Perturbations?
Notably, we are surprised to discover that robustness tends to decrease as fine-tuning (SFT and RLHF) is conducted.
FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data
Federated learning is an emerging distributed machine learning method, enables a large number of clients to train a model without exchanging their local data.
Continual Learning From a Stream of APIs
Next, we train the CL model by minimizing the gap between the responses of the CL model and the black-box API on synthetic data, to transfer the API's knowledge to the CL model.
MerA: Merging Pretrained Adapters For Few-Shot Learning
Adapter tuning, which updates only a few parameters, has become a mainstream method for fine-tuning pretrained language models to downstream tasks.
Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?
The multimedia community has shown a significant interest in perceiving and representing the physical world with multimodal pretrained neural network models, and among them, the visual-language pertaining (VLP) is, currently, the most captivating topic.
Master-slave Deep Architecture for Top-K Multi-armed Bandits with Non-linear Bandit Feedback and Diversity Constraints
We propose a novel master-slave architecture to solve the top-$K$ combinatorial multi-armed bandits problem with non-linear bandit feedback and diversity constraints, which, to the best of our knowledge, is the first combinatorial bandits setting considering diversity constraints under bandit feedback.
Towards Understanding the Generalizability of Delayed Stochastic Gradient Descent
Stochastic gradient descent (SGD) performed in an asynchronous manner plays a crucial role in training large-scale machine learning models.
DFedADMM: Dual Constraints Controlled Model Inconsistency for Decentralized Federated Learning
To address the communication burden issues associated with federated learning (FL), decentralized federated learning (DFL) discards the central server and establishes a decentralized communication network, where each client communicates only with neighboring clients.
LGViT: Dynamic Early Exiting for Accelerating Vision Transformer
Recently, the efficient deployment and acceleration of powerful vision transformers (ViTs) on resource-limited edge devices for providing multimedia services have become attractive tasks.
Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup
Adaptive optimization has achieved notable success for distributed learning while extending adaptive optimizer to federated Learning (FL) suffers from severe inefficiency, including (i) rugged convergence due to inaccurate gradient estimation in global adaptive optimizer; (ii) client drifts exacerbated by local over-fitting with the local adaptive optimizer.
High-Resolution Volumetric Reconstruction for Clothed Humans
We present a novel method for reconstructing clothed humans from a sparse set of, e. g., 1 to 6 RGB images.
GBT: Two-stage transformer framework for non-stationary time series forecasting
It decouples the prediction process of TSFT into two stages, including Auto-Regression stage and Self-Regression stage to tackle the problem of different statistical properties between input and prediction sequences. Prediction results of Auto-Regression stage serve as a Good Beginning, i. e., a better initialization for inputs of Self-Regression stage.
A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
Through this comprehensive survey, we aspire to uncover potential solutions by drawing upon ideas and approaches from various fields that have dealt with forgetting.
Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
To further integrate it with normal training process, we then propose a learnable poisoning sample selection strategy to learn the mask together with the model parameters through a min-max optimization. Specifically, the outer loop aims to achieve the backdoor attack goal by minimizing the loss based on the selected samples, while the inner loop selects hard poisoning samples that impede this goal by maximizing the loss.
Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer
Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of training loss when adding a perturbation to the weight.
Enhancing Adversarial Training via Reweighting Optimization Trajectory
Despite the fact that adversarial training has become the de facto method for improving the robustness of deep neural networks, it is well-known that vanilla adversarial training suffers from daunting robust overfitting, resulting in unsatisfactory robust generalization.
FDNet: Focal Decomposed Network for Efficient, Robust and Practical Time Series Forecasting
Moreover, we propose focal input sequence decomposition method which decomposes input sequence in a focal manner for efficient and robust forecasting when facing Long Sequence Time series Input (LSTI) problem.
One-step Multi-view Clustering with Diverse Representation
In light of this, we propose a one-step multi-view clustering with diverse representation method, which incorporates multi-view learning and $k$-means into a unified framework.
Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning
Recent works have shown the potential of diffusion models in computer vision and natural language processing.
CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification
Although graph neural networks (GNNs) have achieved impressive achievements in graph classification, they often need abundant task-specific labels, which could be extensively costly to acquire.
Are Large Kernels Better Teachers than Transformers for ConvNets?
We hereby carry out a first-of-its-kind study unveiling that modern large-kernel ConvNets, a compelling competitor to Vision Transformers, are remarkably more effective teachers for small-kernel ConvNets, due to more similar architectures.
Compact Real-time Radiance Fields with Neural Codebook
Reconstructing neural radiance fields with explicit volumetric representations, demonstrated by Plenoxels, has shown remarkable advantages on training and rendering efficiency, while grid-based representations typically induce considerable overhead for storage and transmission.
Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data.
Incomplete Multimodal Learning for Complex Brain Disorders Prediction
Especially in studies of brain diseases, research cohorts may include both neuroimaging data and genetic data, but for practical clinical diagnosis, we often need to make disease predictions only based on neuroimages.
Towards More Suitable Personalization in Federated Learning via Decentralized Partial Model Training
Personalized federated learning (PFL) aims to produce the greatest personalized model for each client to face an insurmountable problem--data heterogeneity in real FL systems.
Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape
In federated learning (FL), a cluster of local clients are chaired under the coordination of the global server and cooperatively train one model with privacy protection.
Prompt-Tuning Decision Transformer with Preference Ranking
Our work contributes to the advancement of prompt-tuning approaches in RL, providing a promising direction for optimizing large RL agents for specific preference tasks.
DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation
In this work, firstly, we present a novel self-supervised method for learning dense 3D facial geometry (ie, depth) from face videos, without requiring camera parameters and 3D geometry annotations in training.
Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing
However, it suffers from issues in terms of communication, resource of MTs, and privacy.
Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy
To defend the inference attacks and mitigate the sensitive information leakages in Federated Learning (FL), client-level Differentially Private FL (DPFL) is the de-facto standard for privacy protection by clipping local updates and adding random noise.
Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization
Fine-tuning based on benign data is a natural defense to erase the backdoor effect in a backdoored model.
Evaluate Geometry of Radiance Fields with Low-frequency Color Prior
From this insight, given a reconstructed density field and observation images, we design a closed-form method to approximate the color field with low-frequency spherical harmonics, and compute the inverse mean residual color.
On Efficient Training of Large-Scale Deep Learning Models: A Literature Review
The field of deep learning has witnessed significant progress, particularly in computer vision (CV), natural language processing (NLP), and speech.
Quantum Imitation Learning
Despite remarkable successes in solving various complex decision-making tasks, training an imitation learning (IL) algorithm with deep neural networks (DNNs) suffers from the high computation burden.
Towards Making the Most of ChatGPT for Machine Translation
We show that: 1) The performance of ChatGPT depends largely on temperature, and a lower temperature usually can achieve better performance; 2) Emphasizing the task information can further improve ChatGPT's performance, particularly in complex MT tasks; 3) Introducing domain information can elicit ChatGPT's generalization ability and improve its performance in the specific domain; 4) ChatGPT tends to generate hallucinations for non-English-centric MT tasks, which can be partially addressed by our proposed prompts but still need to be highlighted for the MT/NLP community.
Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization
Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.
Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning
The goal of data-free meta-learning is to learn useful prior knowledge from a collection of pre-trained models without accessing their training data.
Make Landscape Flatter in Differentially Private Federated Learning
Specifically, DP-FedSAM integrates Sharpness Aware Minimization (SAM) optimizer to generate local flatness models with better stability and weight perturbation robustness, which results in the small norm of local updates and robustness to DP noise, thereby improving the performance.
Visual Prompt Based Personalized Federated Learning
Then, the local model is trained on the input composed of raw data and a visual prompt to learn the distribution information contained in the prompt.
Graph Decision Transformer
Offline reinforcement learning (RL) is a challenging task, whose objective is to learn policies from static trajectory data without interacting with the environment.
SGDA: Towards 3D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention
To address this issue, we propose a slice grouped domain attention (SGDA) module to enhance the generalization capability of the pulmonary nodule detection networks.
OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System
Automated machine learning (AutoML) seeks to build ML models with minimal human effort.
AdaSAM: Boosting Sharpness-Aware Minimization with Adaptive Learning Rate and Momentum for Training Deep Neural Networks
Integrating SAM with adaptive learning rate and momentum acceleration, dubbed AdaSAM, has already been explored empirically to train large-scale deep neural networks without theoretical guarantee due to the triple difficulties in analyzing the coupled perturbation step, adaptive learning rate and momentum step.
Subspace based Federated Unlearning
Federated learning (FL) enables multiple clients to train a machine learning model collaboratively without exchanging their local data.
Fusion of Global and Local Knowledge for Personalized Federated Learning
Personalized federated learning, as a variant of federated learning, trains customized models for clients using their heterogeneously distributed data.
Establishing group-level brain structural connectivity incorporating anatomical knowledge under latent space modeling
By applying the ABC model to study brain structural connectivity stratified by sex among Alzheimer's Disease (AD) subjects and healthy controls incorporating the anatomical attributes (volume, thickness and area) on nodes, our method shows superior predictive power on out-of-sample structural connectivity and identifies meaningful sex-specific network neuromarkers for AD.
FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy
Federated learning is an emerging distributed machine learning framework which jointly trains a global model via a large number of local devices with data privacy protections.
Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE
This technical report briefly describes our JDExplore d-team's submission Vega v1 on the General Language Understanding Evaluation (GLUE) leaderboard, where GLUE is a collection of nine natural language understanding tasks, including question answering, linguistic acceptability, sentiment analysis, text similarity, paraphrase detection, and natural language inference.
FedABC: Targeting Fair Competition in Personalized Federated Learning
In particular, we adopt the ``one-vs-all'' training strategy in each client to alleviate the unfair competition between classes by constructing a personalized binary classification problem for each class.
Enhance Local Consistency in Federated Learning: A Multi-Step Inertial Momentum Approach
Federated learning (FL), as a collaborative distributed training paradigm with several edge computing devices under the coordination of a centralized server, is plagued by inconsistent local stationary points due to the heterogeneity of the local partial participation clients, which precipitates the local client-drifts problems and sparks off the unstable and slow convergence, especially on the aggravated heterogeneous dataset.
Improving the Model Consistency of Decentralized Federated Learning
To mitigate the privacy leakages and communication burdens of Federated Learning (FL), decentralized FL (DFL) discards the central server and each client only communicates with its neighbors in a decentralized communication network.
SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning
Offline safe RL is of great practical relevance for deploying agents in real-world applications.
Gene-SGAN: a method for discovering disease subtypes with imaging and genetic signatures via multi-view weakly-supervised deep clustering
Disease heterogeneity has been a critical challenge for precision diagnosis and treatment, especially in neurologic and neuropsychiatric diseases.
MetaMix: Towards Corruption-Robust Continual Learning With Temporally Self-Adaptive Data Transformation
To make them trustworthy and robust to corruptions deployed in safety-critical scenarios, we propose a meta-learning framework of self-adaptive data augmentation to tackle the corruption robustness in CL.
Global Balanced Experts for Federated Long-Tailed Learning
In particular, a proxy is derived from the accumulated gradients uploaded by the clients after local training, and is shared by all clients as the class prior for re-balance training.
Data Augmented Flatness-aware Gradient Projection for Continual Learning
In this paper, we first revisit the gradient projection method from the perspective of flatness of loss surface, and find that unflatness of the loss surface leads to catastrophic forgetting of the old tasks when the projection constraint is reduced to improve the performance of new tasks.
On Transforming Reinforcement Learning by Transformer: The Development Trajectory
Transformer, originally devised for natural language processing, has also attested significant success in computer vision.
SVSBI: Sequence-based virtual screening of biomolecular interactions
Virtual screening (VS) is an essential technique for understanding biomolecular interactions, particularly, drug design and discovery.
Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation
We propose to distil useful target domain information through a co-learning strategy to improve target pseudolabel quality for finetuning the source model.
Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning
On the other hand, the safe agent mimics the baseline agent for policy improvement and learns to fulfill safety constraints via off-policy RL tuning.
Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks
Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there is still a lack of high-quality evaluation of those algorithms that adheres to safety constraints at each decision step under complex and unknown dynamics.
4K-NeRF: High Fidelity Neural Radiance Fields at Ultra High Resolutions
In this paper, we present a novel and effective framework, named 4K-NeRF, to pursue high fidelity view synthesis on the challenging scenarios of ultra high resolutions, building on the methodology of neural radiance fields (NeRF).
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard.
Ranked #1 on
Common Sense Reasoning
on ReCoRD
Compressing Volumetric Radiance Fields to 1 MB
Approximating radiance fields with volumetric grids is one of promising directions for improving NeRF, represented by methods like Plenoxels and DVGO, which achieve super-fast training convergence and real-time rendering.
AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning
In this paper, we propose to measure the task dominance degree of a parameter by the total updates of each task on this parameter.
Curriculum-based Asymmetric Multi-task Reinforcement Learning
To mitigate the negative influence of customizing the one-off training order in curriculum-based AMTL, CAMRL switches its training mode between parallel single-task RL and asymmetric multi-task RL (MTRL), according to an indicator regarding the training time, the overall performance, and the performance gap among tasks.
Streaming Radiance Fields for 3D Video Synthesis
Instead of training a single model that combines all the frames, we formulate the dynamic modeling problem with an incremental learning paradigm in which per-frame model difference is trained to complement the adaption of a base model on the current frame.
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation
Furthermore, RAP can be naturally combined with many existing black-box attack techniques, to further boost the transferability.
Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach
One of the popular solutions is Sharpness-Aware Minimization (SAM), which smooths the loss landscape via minimizing the maximized change of training loss when adding a perturbation to the weight.
Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models
Fine-tuning large pretrained language models on a limited training corpus usually suffers from poor generalization.
Strength-Adaptive Adversarial Training
Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness disparity between natural and robust accuracies, which deviates from robust network's desideratum.
Tensor-Based Multi-Modality Feature Selection and Regression for Alzheimer's Disease Diagnosis
The assessment of Alzheimer's Disease (AD) and Mild Cognitive Impairment (MCI) associated with brain changes remains a challenging task.
On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation
Pre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT).
Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions
Two key challenges arise in this more realistic setting: (i) how to use unlabeled data in the presence of a large amount of unlabeled out-of-distribution (OOD) data; and (ii) how to prevent catastrophic forgetting on previously learned task distributions due to the task distribution shift.
Respecting Time Series Properties Makes Deep Time Series Forecasting Perfect
Thanks to the core idea of respecting time series properties, no matter in which forecasting format, RTNet shows obviously superior forecasting performances compared with dozens of other SOTA time series forecasting baselines in three real-world benchmark datasets.
Improving Task-free Continual Learning by Distributionally Robust Memory Evolution
To address these problems, for the first time, we propose a principled memory evolution framework to dynamically evolve the memory data distribution by making the memory buffer gradually harder to be memorized with distributionally robust optimization (DRO).
Harnessing Out-Of-Distribution Examples via Augmenting Content and Style
Machine learning models are vulnerable to Out-Of-Distribution (OOD) examples, and such a problem has drawn much attention.
Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods
This paper introduces \textit{online bilevel optimization} in which a sequence of time-varying bilevel problems is revealed one after the other.
Local Sample-weighted Multiple Kernel Clustering with Consensus Discriminative Graph
Multiple kernel clustering (MKC) is committed to achieving optimal information fusion from a set of base kernels.
Dynamic Contrastive Distillation for Image-Text Retrieval
Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts its deployment to real-world search scenarios (where the high latency is unacceptable).
Towards Harnessing Feature Embedding for Robust Learning with Noisy Labels
To exploit this effect, the model prediction-based methods have been widely adopted, which aim to exploit the outputs of DNNs in the early stage of learning to correct noisy labels.
SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving
Safe reinforcement learning (RL) has achieved significant success on risk-sensitive tasks and shown promise in autonomous driving (AD) as well.
Understanding Robust Overfitting of Adversarial Training and Beyond
Here, we explore the causes of robust overfitting by comparing the data distribution of \emph{non-overfit} (weak adversary) and \emph{overfitted} (strong adversary) adversarial training, and observe that the distribution of the adversarial data generated by weak adversary mainly contain small-loss data.
DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training
In this work, we propose a novel personalized federated learning framework in a decentralized (peer-to-peer) communication protocol named Dis-PFL, which employs personalized sparse masks to customize sparse local models on the edge.
Robust Weight Perturbation for Adversarial Training
Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation.
Few-Shot Adaptation of Pre-Trained Networks for Domain Shift
Recent test-time adaptation methods update batch normalization layers of pre-trained source models deployed in new target environments with streaming data to mitigate such performance degradation.
Efficient-Adam: Communication-Efficient Distributed Adam
Distributed adaptive stochastic gradient methods have been widely used for large-scale nonconvex optimization, such as training deep learning models.
MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models
In this paper, we develop a general method, which we call MissDAG, to perform causal discovery from data with incomplete observations.
Penalized Proximal Policy Optimization for Safe Reinforcement Learning
Safe reinforcement learning aims to learn the optimal policy while satisfying safety constraints, which is essential in real-world applications.
Interpretable Graph Convolutional Network of Multi-Modality Brain Imaging for Alzheimer's Disease Diagnosis
Identification of brain regions related to the specific neurological disorders are of great importance for biomarker and diagnostic studies.
Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation and Understanding
For multilingual sequence-to-sequence pretrained language models (multilingual Seq2Seq PLMs), e. g. mBART, the self-supervised pretraining task is trained on a wide range of monolingual languages, e. g. 25 languages from CommonCrawl, while the downstream cross-lingual tasks generally progress on a bilingual language subset, e. g. English-German, making there exists the data discrepancy, namely domain discrepancy, and cross-lingual learning objective discrepancy, namely task discrepancy, between the pretraining and finetuning stages.
Robust Unlearnable Examples: Protecting Data Against Adversarial Learning
To address this concern, methods are proposed to make data unlearnable for deep learning models by adding a type of error-minimizing noise.
Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning
Instead, we propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG), which relieves the issue of direct model aggregation.
Self-Supervised Deep Learning to Enhance Breast Cancer Detection on Screening Mammography
A major limitation in applying deep learning to artificial intelligence (AI) systems is the scarcity of high-quality curated datasets.
Depth-Aware Generative Adversarial Network for Talking Head Video Generation
In a more dense way, the depth is also utilized to learn 3D-aware cross-modal (i. e. appearance and depth) attention to guide the generation of motion fields for warping source image representations.
Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance
Even more unconventionally, our proposed method enables directly training sparse unbalanced GANs with an extremely sparse generator from scratch.
Provably Efficient Convergence of Primal-Dual Actor-Critic with Nonlinear Function Approximation
We study the convergence of the actor-critic algorithm with nonlinear function approximation under a nonconvex-nonconcave primal-dual formulation.
The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training
In this paper, we focus on sparse training and highlight a perhaps counter-intuitive finding, that random pruning at initialization can be quite powerful for the sparse training of modern neural networks.
Achieving Personalized Federated Learning with Sparse Local Models
To counter this issue, personalized FL (PFL) was proposed to produce dedicated local models for each individual user.
Learning To Learn and Remember Super Long Multi-Domain Task Sequence
We propose a domain shift detection technique to capture latent domain change and equip the meta optimizer with it to work in this setting.
MSG-SR-Net: A Weakly Supervised Network Integrating Multi-Scale Generation and Super-Pixel Refinement for Building Extraction from High-Resolution Remotely Sensed Imageries
The MSG module is proposed to use global semantic information to guide the learning of multiple features across different levels, and then respectively to utilize multi-level features for generating multi-scale CAMs.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
DGL-GAN: Discriminator Guided Learning for GAN Compression
Moreover, DGL-GAN is also effective in boosting the performance of original uncompressed GANs.
Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layer
Bayesian neural networks (BNNs) have become a principal approach to alleviate overconfident predictions in deep learning, but they often suffer from scaling issues due to a large number of distribution parameters.
FedDAG: Federated DAG Structure Learning
To date, most directed acyclic graphs (DAGs) structure learning approaches require data to be stored in a central server.
FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks
To bridge the gap and facilitate the development of FL for computer vision tasks, in this work, we propose a federated learning library and benchmarking framework, named FedCV, to evaluate FL on the three most representative computer vision tasks: image classification, image segmentation, and object detection.
Off-policy Imitation Learning from Visual Inputs
We propose OPIfVI (Off-Policy Imitation from Visual Inputs), which is composed of an off-policy learning manner, data augmentation, and encoder techniques, to tackle the mentioned challenges, respectively.
Multidimensional representations in late-life depression: convergence in neuroimaging, cognition, clinical symptomatology and genetics
We sought to delineate, cross-sectionally and longitudinally, disease-related heterogeneity in LLD linked to neuroanatomy, cognitive functioning, clinical symptomatology, and genetic profiles.
On Heterogeneously Distributed Data, Sparsity Matters
Federated learning (FL) is particularly vulnerable to heterogeneously distributed data, since a common global model in FL may not adapt to the heterogeneous data distribution of each user.
FLBoost: On-the-Fly Fine-tuning Boosts Federated Learning via Data-free Distillation
On the contrary, we propose a new solution: on-the-fly fine-tuning the global model in server via data-free distillation to boost its performance, dubbed FLBoost to relieve the issue of direct model aggregation.
Sparse Unbalanced GAN Training with In-Time Over-Parameterization
Perhaps most importantly, we find instead of inheriting parameters from expensive pre-trained GANs, directly training sparse GANs from scratch can be a much more efficient solution.
On Learning to Solve Cardinality Constrained Combinatorial Optimization in One-Shot: A Re-parameterization Approach via Gumbel-Sinkhorn-TopK
Cardinality constrained combinatorial optimization requires selecting an optimal subset of $k$ elements, and it will be appealing to design data-driven algorithms that perform TopK selection over a probability distribution predicted by a neural network.
Lagrangian Generative Adversarial Imitation Learning with Safety
Imitation Learning (IL) merely concentrates on reproducing expert behaviors and could take dangerous actions, which is unbearable in safety-critical scenarios.
Source-Free Few-Shot Domain Adaptation
Test-time adaptation of pre-trained source models with streaming unlabelled target data is an attractive setting that protects the privacy of source data, but it has mini-batch size and class-distribution requirements on the streaming data which might not be desirable in practice.
Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial Learning
To address this concern, methods are proposed to make data unlearnable for deep learning models by adding a type of error-minimizing noise.
Enabling variable high spatial resolution retrieval from a long pulse BOTDA sensor
We propose a convolutional neural network (CNN) to process the data of conventional Brillouin optical time domain analysis (BOTDA) sensors, which achieves unprecedented performance improvement that allows to directly retrieve higher spatial resolution (SR) from the sensing system that use long pump pulses.
Learning Meta Representations for Agents in Multi-Agent Reinforcement Learning
In multi-agent reinforcement learning, the behaviors that agents learn in a single Markov Game (MG) are typically confined to the given agent number.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
TCCT: Tightly-Coupled Convolutional Transformer on Time Series Forecasting
To address this issue, we propose the concept of tightly-coupled convolutional Transformer(TCCT) and three TCCT architectures which apply transformed CNN architectures into Transformer: (1) CSPAttention: through fusing CSPNet with self-attention mechanism, the computation cost of self-attention mechanism is reduced by 30% and the memory usage is reduced by 50% while achieving equivalent or beyond prediction accuracy.
End-to-End Adaptive Monte Carlo Denoising and Super-Resolution
We show in this work that Monte Carlo path tracing can be further accelerated by joint super-resolution and denoising (SRD) in post-processing.
UniFaceGAN: A Unified Framework for Temporally Consistent Facial Video Editing
Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.
S2Looking: A Satellite Side-Looking Dataset for Building Change Detection
This paper therefore introduces S2Looking, a building-change-detection dataset that contains large-scale side-looking satellite images captured at various off-nadir angles.
Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before-training pruning (pruning at initialization).
Ranked #3 on
Sparse Learning
on ImageNet
Local AdaGrad-Type Algorithm for Stochastic Convex-Concave Optimization
Large scale convex-concave minimax problems arise in numerous applications, including game theory, robust training, and training of generative adversarial networks.
Structure-Regularized Attention for Deformable Object Representation
Capturing contextual dependencies has proven useful to improve the representational power of deep neural networks.
Attacking Adversarial Attacks as A Defense
In this work, we find that the adversarial attacks can also be vulnerable to small perturbations.
Differentiable Neural Architecture Search for Extremely Lightweight Image Super-Resolution
Specifically, the cell-level search space is designed based on an information distillation mechanism, focusing on the combinations of lightweight operations and aiming to build a more lightweight and accurate SR structure.
Robust Registration of Multimodal Remote Sensing Images Based on Structural Similarity
Moreover, a robust registration method is also proposed in this paper based on HOPCncc, which is evaluated using six pairs of multimodal remote sensing images.
Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration
Adam is one of the most influential adaptive stochastic algorithms for training deep neural networks, which has been pointed out to be divergent even in the simple convex setting via a few simple counterexamples.
Adaptive Compact Attention For Few-shot Video-to-video Translation
This paper proposes an adaptive compact attention model for few-shot video-to-video translation.
Stochastic Client Selection for Federated Learning with Volatile Clients
Federated Learning (FL), arising as a privacy-preserving machine learning paradigm, has received notable attention from the public.
Functional Connectome Fingerprint Gradients in Young Adults
Our differential identifiability results show that the fingerprint gradients based on genetic and environmental similarities are indeed present when comparing FCs for all parcellations and fMRI conditions.
A Distributed Training Algorithm of Generative Adversarial Networks with Quantized Gradients
In this paper, we propose a {distributed GANs training algorithm with quantized gradient, dubbed DQGAN,} which is the first distributed training method with quantized gradient for GANs.
Improving the spatial resolution of a BOTDA sensor using deconvolution algorithm
The frequency dependency of Brillouin gain temporal envelope is investigated by simulation, and its impact on the recovered results of deconvolution algorithm is thoroughly analyzed.
Network reinforcement driven drug repurposing for COVID-19 by exploiting disease-gene-drug associations
To reduce trial and error in finding treatments for COVID-19, we propose building a network-based drug repurposing framework to prioritize repurposable drugs.
Grouping effects of sparse CCA models in variable selection
The sparse canonical correlation analysis (SCCA) is a bi-multivariate association model that finds sparse linear combinations of two sets of variables that are maximally correlated with each other.
FedML: A Research Library and Benchmark for Federated Machine Learning
Federated learning (FL) is a rapidly growing research field in machine learning.
Task-agnostic Temporally Consistent Facial Video Editing
Compared with the state-of-the-art facial image editing methods, our framework generates video portraits that are more photo-realistic and temporally smooth.
Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning
Extracting effective deep features to represent content and style information is the key to universal style transfer.
AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks
To this end, we propose a fully differentiable search framework for generative adversarial networks, dubbed alphaGAN.
CPOT: Channel Pruning via Optimal Transport
Recent advances in deep neural networks (DNNs) lead to tremendously growing network parameters, making the deployments of DNNs on platforms with limited resources extremely difficult.
Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks
In this paper, we study distributed algorithms for large-scale AUC maximization with a deep neural network as a predictive model.
Quantized Adam with Error Feedback
In this paper, we present a distributed variant of adaptive stochastic gradient method for training deep neural networks in the parameter-server model.
MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation
To remedy this, this paper proposes \mldas, a mixed-level reformulation for NAS that can be optimized efficiently and reliably.
Cognitive Biomarker Prioritization in Alzheimer's Disease using Brain Morphometric Data
This method learns the latent scoring function that pushes the most effective cognitive assessments onto the top of the prioritization list.
Generalized Embedding Machines for Recommender Systems
In this work, we propose an alternative approach to model high-order interaction signals in the embedding level, namely Generalized Embedding Machine (GEM).
Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning
In this paper, we propose a novel deep learning model called Task Adaptive Activation Network (TAAN) that can automatically learn the optimal network architecture for MTL.
MAP Inference via L2-Sphere Linear Program Reformulation
Thus, LS-LP is equivalent to the original MAP inference problem.
Drug-drug interaction prediction based on co-medication patterns and graph matching
Background: The problem of predicting whether a drug combination of arbitrary orders is likely to induce adverse drug reactions is considered in this manuscript.
A Sufficient Condition for Convergences of Adam and RMSProp
Adam and RMSProp are two of the most influential adaptive stochastic algorithms for training deep neural networks, which have been pointed out to be divergent even in the convex setting via a few simple counterexamples.
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
We also propose a parametric gather-excite operator pair which yields further performance gains, relate it to the recently-introduced Squeeze-and-Excitation Networks, and analyse the effects of these changes to the CNN feature activation statistics.
A Unified Analysis of AdaGrad with Weighted Aggregation and Momentum Acceleration
Integrating adaptive learning rate and momentum techniques into SGD leads to a large class of efficiently accelerated adaptive stochastic algorithms, such as AdaGrad, RMSProp, Adam, AccAdaGrad, \textit{etc}.
Image Registration and Predictive Modeling: Learning the Metric on the Space of Diffeomorphisms
We present a method for metric optimization in the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework, by treating the induced Riemannian metric on the space of diffeomorphisms as a kernel in a machine learning context.
Comparator Networks
Our contributions are: (i) We propose a Deep Comparator Network (DCN) that can ingest a pair of sets (each may contain a variable number of images) as inputs, and compute a similarity between the pair--this involves attending to multiple discriminative local regions (landmarks), and comparing local descriptors between pairs of faces; (ii) To encourage high-quality representations for each set, internal competition is introduced for recalibration based on the landmark score; (iii) Inspired by image retrieval, a novel hard sample mining regime is proposed to control the sampling process, such that the DCN is complementary to the standard image classification models.
An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method
Specifically, we find that a large class of primal and primal-dual operator splitting algorithms are all special cases of VMOR-HPE.
Drug Recommendation toward Safe Polypharmacy
Adverse drug reactions (ADRs) induced from high-order drug-drug interactions (DDIs) due to polypharmacy represent a significant public health problem.
A Decomposition Algorithm for the Sparse Generalized Eigenvalue Problem
The sparse generalized eigenvalue problem arises in a number of standard and modern statistical learning models, including sparse principal component analysis, sparse Fisher discriminant analysis, and sparse canonical correlation analysis.
Numerical Analysis
End-to-end Training for Whole Image Breast Cancer Diagnosis using An All Convolutional Design
We also demonstrate that a whole image model trained on DDSM can be easily transferred to INbreast without using its lesion annotations and using only a small amount of training data.
VGGFace2: A dataset for recognising faces across pose and age
The dataset was collected with three goals in mind: (i) to have both a large number of identities and also a large number of images for each identity; (ii) to cover a large range of pose, age and ethnicity; and (iii) to minimize the label noise.
Ranked #1 on
Face Verification
on IJB-C
(training dataset metric)
Squeeze-and-Excitation Networks
Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2. 251%, surpassing the winning entry of 2016 by a relative improvement of ~25%.
Ranked #59 on
Image Classification
on CIFAR-10
Deep Learning to Improve Breast Cancer Early Detection on Screening Mammography
We also demonstrate that a whole image classifier trained using our end-to-end approach on the DDSM digitized film mammograms can be transferred to INbreast FFDM images using only a subset of the INbreast data for fine-tuning and without further reliance on the availability of lesion annotations.
Ranked #15 on
Cancer-no cancer per image classification
on CBIS-DDSM
Breast Cancer Detection
Cancer-no cancer per image classification
+1
