Search Results for author:
Found 64 papers, 37 papers with code
SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion
Multivariate time series forecasting plays a crucial role in various fields such as finance, traffic management, energy, and healthcare.
TV100: A TV Series Dataset that Pre-Trained CLIP Has Not Seen
The era of pre-trained models has ushered in a wealth of new insights for the machine learning community.
MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classes
For better model personalization, we point out that the hard-won personalized models are not well exploited and propose "inherited private model" to store the personalization experience.
DIDA: Denoised Imitation Learning based on Domain Adaptation
Imitating skills from low-quality datasets, such as sub-optimal demonstrations and observations with distractors, is common in real-world applications.
SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring
In many real-world visual Imitation Learning (IL) scenarios, there is a misalignment between the agent's and the expert's perspectives, which might lead to the failure of imitation.
Bridge the Modality and Capacity Gaps in Vision-Language Model Selection
It then uses this matrix to transfer useful statistics of VLMs from open-source datasets to the target dataset for bridging those two gaps and enhancing the VLM's capacity estimation for VLM selection.
Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning
Despite the strong performance of Pre-Trained Models (PTMs) in CIL, a critical issue persists: learning new classes often results in the overwriting of old ones.
AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors
Model-based methods have significantly contributed to distinguishing task-irrelevant distractors for visual control.
Continual Learning with Pre-Trained Models: A Survey
Nowadays, real-world applications often face streaming data, which requires the learning system to absorb new knowledge as data evolves.
Twice Class Bias Correction for Imbalanced Semi-Supervised Learning
Differing from traditional semi-supervised learning, class-imbalanced semi-supervised learning presents two distinct challenges: (1) The imbalanced distribution of training samples leads to model bias towards certain classes, and (2) the distribution of unlabeled samples is unknown and potentially distinct from that of labeled samples, which further contributes to class bias in the pseudo-labels during training.
CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learning
For each pseudo-labeled sample, we select positive and negative samples from labeled data instead of unlabeled data to compute contrastive loss.
Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
In this Few-Shot Class-Incremental Learning (FSCIL) scenario, existing methods either introduce extra learnable components or rely on a frozen feature extractor to mitigate catastrophic forgetting and overfitting problems.
Learning Robust Precipitation Forecaster by Temporal Frame Interpolation
This achievement not only underscores the effectiveness of our methodologies but also establishes a new standard for deep learning applications in weather forecasting.
Training-Free Generalization on Heterogeneous Tabular Data via Meta-Representation
Tabular data is prevalent across various machine learning domains.
Unlocking the Transferability of Tokens in Deep Models for Tabular Data
Fine-tuning a pre-trained deep neural network has become a successful paradigm in various machine learning tasks.
RE-SORT: Removing Spurious Correlation in Multilevel Interaction for CTR Prediction
Click-through rate (CTR) prediction is a critical task in recommendation systems, serving as the ultimate filtering step to sort items for a user.
PILOT: A Pre-Trained Model-Based Continual Learning Toolbox
While traditional machine learning can effectively tackle a wide range of problems, it primarily operates within a closed-world setting, which presents limitations when dealing with streaming data.
ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse
The rapid expansion of foundation pre-trained models and their fine-tuned counterparts has significantly contributed to the advancement of machine learning.
Streaming CTR Prediction: Rethinking Recommendation Task for Real-World Streaming Data
The Click-Through Rate (CTR) prediction task is critical in industrial recommender systems, where models are usually deployed on dynamic streaming data in practical applications.
SeMAIL: Eliminating Distractors in Visual Imitation via Separated Models
Model-based imitation learning (MBIL) is a popular reinforcement learning method that improves sample efficiency on high-dimension input sources, such as images and videos.
COURIER: Contrastive User Intention Reconstruction for Large-Scale Pre-Train of Image Features
To this end, we propose a recommendation-aware image pre-training method that can learn visual features from user click histories.
IDToolkit: A Toolkit for Benchmarking and Developing Inverse Design Algorithms in Nanophotonics
These obstacles prevent AI researchers from developing specialized methods for scientific designs.
Learning without Forgetting for Vision-Language Models
While traditional CIL methods focus on visual information to grasp core features, recent advances in Vision-Language Models (VLM) have shown promising capabilities in learning generalizable representations with the aid of textual information.
MrTF: Model Refinery for Transductive Federated Learning
We propose a novel learning paradigm named transductive federated learning (TFL) to simultaneously consider the structural information of the to-be-inferred data.
Preserving Locality in Vision Transformers for Class Incremental Learning
In this paper, we encourage the model to preserve more local information as the training procedure goes on and devise a Locality-Preserved Attention (LPA) layer to emphasize the importance of local features.
The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting
Our results conclude that the CD approach has higher capacity but often lacks robustness to accurately predict distributionally drifted time series.
Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need
ADAM is a general framework that can be orthogonally combined with any parameter-efficient tuning method, which holds the advantages of PTM's generalizability and adapted model's adaptivity.
Deep Class-Incremental Learning: A Survey
Deep models, e. g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world.
On Pseudo-Labeling for Class-Mismatch Semi-Supervised Learning
Based on the findings, we propose to improve PL in class-mismatched SSL with two components -- Re-balanced Pseudo-Labeling (RPL) and Semantic Exploration Clustering (SEC).
Learning Debiased Representations via Conditional Attribute Interpolation
When a dataset is biased, i. e., most samples have attributes spuriously correlated with the target label, a Deep Neural Network (DNN) is prone to make predictions by the "unintended" attribute, especially if it is easier to learn.
Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again
Complex teachers tend to be over-confident and traditional temperature scaling limits the efficacy of {\it class discriminability}, resulting in less discriminative wrong class probabilities.
Avoid Overfitting User Specific Information in Federated Keyword Spotting
Federated KWS (FedKWS) could serve as a solution without directly sharing users' data.
Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems
We propose a generalized delayed feedback model (GDFM) that unifies both post-click behaviors and early conversions as stochastic post-click information, which could be utilized to train GDFM in a streaming manner efficiently.
Augmentation Component Analysis: Modeling Similarity via the Augmentation Overlaps
Self-supervised learning aims to learn a embedding space where semantically similar samples are close.
A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
We find that when counting the model size into the total budget and comparing methods with aligned memory size, saving models do not consistently work, especially for the case with limited memory budgets.
Generalized Knowledge Distillation via Relationship Matching
Instead of enforcing the teacher to work on the same task as the student, we borrow the knowledge from a teacher trained from a general label space -- in this "Generalized Knowledge Distillation (GKD)", the classes of the teacher and the student may be the same, completely different, or partially overlapped.
Selective Cross-Task Distillation
Our method reuses cross-task knowledge from a distinct label space and efficiently assesses teachers without enumerating the model repository.
FOSTER: Feature Boosting and Compression for Class-Incremental Learning
The ability to learn new concepts continually is necessary in this ever-changing world.
Ranked #1 on
Incremental Learning
on ImageNet100 - 20 steps
Identifying Ambiguous Similarity Conditions via Semantic Matching
To this end, we introduce a novel evaluation criterion by predicting the comparison's correctness after assigning the learned embeddings to their optimal conditions, which measures how much WS-CSL could cover latent semantics as the supervised model.
Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks
In this work, we propose a new paradigm for FSCIL based on meta-learning by LearnIng Multi-phase Incremental Tasks (LIMIT), which synthesizes fake FSCIL tasks from the base dataset.
Ranked #5 on
Few-Shot Class-Incremental Learning
on CIFAR-100
Federated Learning with Position-Aware Neurons
The permutation invariance property of neural networks and the non-i. i. d.
Forward Compatible Few-Shot Class-Incremental Learning
Forward compatibility requires future new classes to be easily incorporated into the current model based on the current stage data, and we seek to realize it by reserving embedding space for future new classes.
Ranked #4 on
Few-Shot Class-Incremental Learning
on CIFAR-100
PyCIL: A Python Toolbox for Class-Incremental Learning
Traditional machine learning systems are deployed under the closed-world setting, which requires the entire training data before the offline training process.
RID-Noise: Towards Robust Inverse Design under Noisy Environments
We also define a sample-wise weight, which can be used in the maximum weighted likelihood estimation of an inverse model based on a cINN.
LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates
During long-time observations, agents can build \textit{awareness} for teammates to alleviate the problem of partial observability.
Co-Transport for Class-Incremental Learning
As a result, we propose CO-transport for class Incremental Learning (COIL), which learns to relate across incremental tasks with the class-wise semantic relationship.
Preliminary Steps Towards Federated Sentiment Classification
Automatically mining sentiment tendency contained in natural language is a fundamental research to some artificial intelligent applications, where solutions alternate with challenges.
Aggregate or Not? Exploring Where to Privatize in DNN Based Federated Learning Under Different Non-IID Scenes
We advocate the proposed methods could serve as a preliminary try to explore where to privatize for a novel non-iid scene.
Few-Shot Learning with a Strong Teacher
Many existing works take the meta-learning approach, constructing a few-shot learner that can learn from few-shot examples to generate a classifier.
Contextualizing Meta-Learning via Learning to Decompose
To this end, we propose Learning to Decompose Network (LeadNet) to contextualize the meta-learned ``support-to-target'' strategy, leveraging the context of instances with one or mixed latent attributes in a support set.
Semi-Supervised Multi-Modal Multi-Instance Multi-Label Deep Network with Optimal Transport
Moreover, we introduce the extrinsic unlabeled multi-modal multi-instance data, and propose the M3DNS, which considers the instance-level auto-encoder for single modality and modified bag-level optimal transport to strengthen the consistency among modalities.
Towards Enabling Meta-Learning from Target Models
Different from $\mathcal{S}$/$\mathcal{Q}$ protocol, we can also evaluate a task-specific solver by comparing it to a target model $\mathcal{T}$, which is the optimal model for this task or a model that behaves well enough on this task ($\mathcal{S}$/$\mathcal{T}$ protocol).
Few-Shot Action Recognition with Compromised Metric via Optimal Transport
In detail, given two videos, we sample segments from them and cast the calculation of their distance as an optimal transport problem between two segment sequences.
Procrustean Training for Imbalanced Deep Learning
To correct these wrong predictions, the neural network then must focus on pushing features of minor class data across the decision boundaries between major and minor classes, leading to much larger gradients for features of minor classes.
Learning Placeholders for Open-Set Recognition
To this end, we proposed to learn PlaceholdeRs for Open-SEt Recognition (Proser), which prepares for the unknown classes by allocating placeholders for both data and classifier.
Capturing Delayed Feedback in Conversion Rate Prediction via Elapsed-Time Sampling
To strike a balance in this trade-off, we propose Elapsed-Time Sampling Delayed Feedback Model (ES-DFM), which models the relationship between the observed conversion distribution and the true conversion distribution.
Revisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
Meta-learning has become a practical approach towards few-shot image classification, where "a strategy to learn a classifier" is meta-learned on labeled base classes and can be applied to tasks with novel classes.
Unsupervised Few-Shot Image Classification
Unsupervised Few-Shot Learning
Revisiting Meta-Learning as Supervised Learning
Recent years have witnessed an abundance of new publications and approaches on meta-learning.
Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning
Classifiers trained with class-imbalanced data are known to perform poorly on test data of the "minor" classes, of which we have insufficient training data.
Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning
In this paper, we investigate the problem of generalized few-shot learning (GFSL) -- a model during the deployment is required to learn about tail categories with few shots and simultaneously classify the head classes.
Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels.
Rectify Heterogeneous Models with Semantic Mapping
On the way to the robust learner for real-world applications, there are still great challenges, including considering unknown environments with limited data.
What Makes Objects Similar: A Unified Multi-Metric Learning Approach
In UM2L, a type of combination operator is introduced for distance characterization from multiple perspectives, and thus can introduce flexibilities for representing and utilizing both spatial and semantic linkages.
