Search Results for author:
Found 184 papers, 86 papers with code
Don't Waste Your Bits! Squeeze Activations and Gradients for Deep Neural Networks via TinyScript
Recent years have witnessed intensive research interests on training deep neural networks (DNNs) more efficiently by quantization-based compression methods, which facilitate DNNs training in two ways: (1) activations are quantized to shrink the memory consumption, and (2) gradients are quantized to decrease the communication cost.
Analysis of Distributed Optimization Algorithms on a Real Processing-In-Memory System
Processor-centric architectures (e. g., CPU, GPU) commonly used for modern ML training workloads are limited by the data movement bottleneck, i. e., due to repeatedly accessing the training dataset.
Mechanistic Design and Scaling of Hybrid Architectures
The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale model training and evaluation.
TablePuppet: A Generic Framework for Relational Federated Learning
In this paper, we formalize this problem as relational federated learning (RFL).
Negative Yields Positive: Unified Dual-Path Adapter for Vision-Language Models
Recently, large-scale pre-trained Vision-Language Models (VLMs) have demonstrated great potential in learning open-world visual representations, and exhibit remarkable performance across a wide range of downstream tasks through efficient fine-tuning.
HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation
Being able to understand visual scenes is a precursor for many downstream tasks, including autonomous driving, robotics, and other vision-based approaches.
Test-time Distribution Learning Adapter for Cross-modal Visual Reasoning
Several approaches aim to efficiently adapt VLP models to downstream tasks with limited supervision, aiming to leverage the acquired knowledge from VLP models.
Concept-Guided Prompt Learning for Generalization in Vision-Language Models
However, for generalization tasks, the current fine-tuning methods for CLIP, such as CoOp and CoCoOp, demonstrate relatively low performance on some fine-grained datasets.
A Simple LLM Framework for Long-Range Video Question-Answering
Furthermore, we show that a specialized prompt that asks the LLM first to summarize the noisy short-term visual captions and then answer a given input question leads to a significant LVQA performance boost.
Ranked #1 on
Zero-Shot Video Question Answer
on NExT-GQA
WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data
Together with the pipeline, we will additionally release 9. 5M urls to word documents which can be processed using WordScape to create a dataset of over 40M pages.
DMLR: Data-centric Machine Learning Research -- Past, Present and Future
Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure development for the creation of next-generation public datasets that will advance machine learning science.
Learning to Adapt CLIP for Few-Shot Monocular Depth Estimation
When CLIP is used for depth estimation tasks, the patches, divided from the input images, can be combined with a series of semantic descriptions of the depth information to obtain similarity results.
Object-centric Video Representation for Long-term Action Anticipation
To recognize and predict human-object interactions, we use a Transformer-based neural architecture which allows the "retrieval" of relevant objects for action anticipation at various time scales.
Ranked #2 on
Long Term Action Anticipation
on Ego4D
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
We show that contextual sparsity exists, that it can be accurately predicted, and that we can exploit it to speed up LLM inference in wall-clock time without compromising LLM's quality or in-context learning ability.
Effective and Efficient Federated Tree Learning on Hybrid Data
To address this, we propose HybridTree, a novel federated learning approach that enables federated tree learning on hybrid data.
Document-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language Models
Relation extraction aims at inferring structured human knowledge from textual documents.
DSG: An End-to-End Document Structure Generator
To the best of our knowledge, our DSG system is the first end-to-end trainable system for hierarchical document parsing.
Towards General and Efficient Online Tuning for Spark
The distributed data analytic system -- Spark is a common choice for processing massive volumes of heterogeneous data, while it is challenging to tune its parameters to achieve high performance.
BDC-Adapter: Brownian Distance Covariance for Better Vision-Language Reasoning
Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP and ALIGN, have introduced a new paradigm for learning transferable visual representations.
BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural Networks
To handle graphs in which features or connectivities are evolving over time, a series of temporal graph neural networks (TGNNs) have been proposed.
Unsupervised Prototype Adapter for Vision-Language Models
To leverage the valuable knowledge encoded within these models for downstream tasks, several fine-tuning approaches, including prompt tuning methods and adapter-based methods, have been developed to adapt vision-language models effectively with supervision.
AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
We propose to formulate the LTA task from two perspectives: a bottom-up approach that predicts the next actions autoregressively by modeling temporal dynamics; and a top-down approach that infers the goal of the actor and plans the needed procedure to accomplish the goal.
Cross-Modal Concept Learning and Inference for Vision-Language Models
Based on these visual concepts, we construct a discriminative representation of images and learn a concept inference network to perform downstream image classification tasks, such as few-shot learning and domain generalization.
Improving Retrieval-Augmented Large Language Models via Data Importance Learning
There are exponentially many terms in the multilinear extension, and one key contribution of this paper is a polynomial time algorithm that computes exactly, given a retrieval-augmented model with an additive utility function and a validation set, the data importance of data points in the retrieval corpus using the multilinear extension of the model's utility function.
MotionTrack: End-to-End Transformer-based Multi-Object Tracing with LiDAR-Camera Fusion
Multiple Object Tracking (MOT) is crucial to autonomous vehicle perception.
SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving
On the other hand, unknown objects, which have not been seen in training sample set, are one of the reasons that hinder autonomous vehicles from driving beyond the operational domain.
OpenBox: A Python Toolkit for Generalized Black-box Optimization
Black-box optimization (BBO) has a broad range of applications, including automatic machine learning, experimental design, and database knob tuning.
Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems
Given an unknown dynamical system, what is the minimum number of samples needed for effective learning of its governing laws and accurate prediction of its future evolution behavior, and how to select these critical samples?
Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation
This strong correlation suggests that we can use this error as feedback to guide the correction process.
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
As a result, when running OPT-175B on a single 16GB GPU, FlexGen achieves significantly higher throughput compared to state-of-the-art offloading systems, reaching a generation throughput of 1 token/s for the first time with an effective batch size of 144.
Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation
We observe that the performance of this feed-forward Hebbian learning for fully test-time adaptation can be significantly improved by incorporating a feedback neuro-modulation layer.
Hierarchical Classification of Research Fields in the "Web of Science" Using Deep Learning
This paper presents a hierarchical classification system that automatically categorizes a scholarly publication using its abstract into a three-tier hierarchical label set (discipline, field, subfield) in a multi-class setting.
Convolution-enhanced Evolving Attention Networks
To the best of our knowledge, this is the first work that explicitly models the layer-wise evolution of attention maps.
Holistic Evaluation of Language Models
We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models.
EEG-Fest: Few-shot based Attention Network for Driver's Vigilance Estimation with EEG Signals
A lack of driver's vigilance is the main cause of most vehicle crashes.
Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation
Instead of learning a single prototype for each class, in this paper, we propose to use an adaptive number of prototypes to dynamically describe the different point patterns within a semantic class.
Ranked #17 on
3D Semantic Segmentation
on SemanticKITTI
Neural Methods for Logical Reasoning Over Knowledge Graphs
We introduce a set of models that use Neural Networks to create one-point vector embeddings to answer the queries.
CARE: Certifiably Robust Learning with Reasoning via Variational Inference
In particular, we propose a certifiably robust learning with reasoning pipeline (CARE), which consists of a learning component and a reasoning component.
DataPerf: Benchmarks for Data-Centric AI Development
Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems.
Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM
To address these challenges, in this paper, we introduce a VFL framework with multiple heads (VIM), which takes the separate contribution of each client into account, and enables an efficient decomposition of the VFL optimization objective to sub-objectives that can be iteratively tackled by the server and the clients on their own.
GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks
As GNN models are deployed to more mission-critical applications, we are in dire need for a common evaluation protocol of explainability methods of GNNs.
Efficient End-to-End AutoML via Scalable Search Space Decomposition
End-to-end AutoML has attracted intensive interests from both academia and industry which automatically searches for ML pipelines in a space induced by feature engineering, algorithm/model selection, and hyper-parameter tuning.
Contrastive Learning for Unsupervised Domain Adaptation of Time Series
To the best of our knowledge, ours is the first framework to learn domain-invariant, contextual representation for UDA of time series data.
Stochastic Gradient Descent without Full Data Shuffle
In this paper, we first conduct a systematic empirical study on existing data shuffling strategies, which reveals that all existing strategies have room for improvement -- they all suffer in terms of I/O performance or convergence rate.
FedHPO-B: A Benchmark Suite for Federated Hyperparameter Optimization
Due to this uniqueness, existing HPO benchmarks no longer satisfy the need to compare HPO methods in the FL setting.
Transfer Learning based Search Space Design for Hyperparameter Tuning
The extensive experiments show that our approach considerably boosts BO by designing a promising and compact search space instead of using the entire space, and outperforms the state-of-the-arts on a wide range of benchmarks, including machine learning and deep learning tuning tasks, and neural architecture search.
TransBO: Hyperparameter Optimization via Two-Phase Transfer Learning
With the extensive applications of machine learning models, automatic hyperparameter optimization (HPO) has become increasingly important.
Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees
Communication compression is a crucial technique for modern distributed learning systems to alleviate their communication bottlenecks over slower networks.
Decentralized Training of Foundation Models in Heterogeneous Environments
Our key technical contribution is a scheduling algorithm that allocates different computational "tasklets" in the training of foundation models to a group of decentralized GPU devices connected by a slow heterogeneous network.
Certifying Some Distributional Fairness with Subpopulation Decomposition
In this paper, we first formulate the certified fairness of an ML model trained on a given data distribution as an optimization problem based on the model performance loss bound on a fairness constrained distribution, which is within bounded distributional distance with the training distribution.
BRIGHT -- Graph Neural Networks in Real-Time Fraud Detection
Apart from rule-based and machine learning filters that are already deployed in production, we want to enable efficient real-time inference with graph neural networks (GNNs), which is useful to catch multihop risk propagation in a transaction graph.
Data Debugging with Shapley Importance over End-to-End Machine Learning Pipelines
We present DataScope (ease. ml/datascope), the first system that efficiently computes Shapley values of training examples over an end-to-end ML pipeline, and illustrate its applications in data debugging for ML training.
Modelling graph dynamics in fraud detection with "Attention"
At online retail platforms, detecting fraudulent accounts and transactions is crucial to improve customer experience, minimize loss, and avoid unauthorized transactions.
SHiFT: An Efficient, Flexible Search Engine for Transfer Learning
Transfer learning can be seen as a data- and compute-efficient alternative to training models from scratch.
A Quality Index Metric and Method for Online Self-Assessment of Autonomous Vehicles Sensory Perception
The results demonstrate that the proposed evaluation metric accurately assesses the detection quality of camera-based systems in autonomous driving environments.
An attention-based U-Net for detecting deforestation within satellite sensor imagery
In this paper, we implement and analyse an Attention U-Net deep network for semantic segmentation using Sentinel-2 satellite sensor imagery, for the purpose of detecting deforestation within two forest biomes in South America, the Amazon Rainforest and the Atlantic Forest.
Certifying Out-of-Domain Generalization for Blackbox Functions
As a result, the wider application of these techniques is currently limited by its scalability and flexibility -- these techniques often do not scale to large-scale datasets with modern deep neural networks or cannot handle loss functions which may be non-smooth such as the 0-1 loss.
ReforesTree: A Dataset for Estimating Tropical Forest Carbon Stock with Deep Learning and Aerial Imagery
The potential for impact and scale of leveraging advancements in machine learning and remote sensing technologies is promising but needs to be of high quality in order to replace the current forest stock protocols for certifications.
Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scale
The ever-growing demand and complexity of machine learning are putting pressure on hyper-parameter tuning systems: while the evaluation cost of models continues to increase, the scalability of state-of-the-arts starts to become a crucial bottleneck.
TableParser: Automatic Table Parsing with Weak Supervision from Spreadsheets
Tables have been an ever-existing structure to store data.
Super-resolution reconstruction of cytoskeleton image based on A-net deep learning network
To date, live-cell imaging at the nanometer scale remains challenging.
Dynamic Human Evaluation for Relative Model Comparisons
Collecting human judgements is currently the most reliable evaluation method for natural language generation systems.
Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters
Specifically, in order to ensure both the training efficiency and the training accuracy, we design a novel hybrid training algorithm, where the embedding layer and the dense neural network are handled by different synchronization mechanisms; then we build a system called Persia (short for parallel recommendation training system with hybrid acceleration) to support this hybrid training algorithm.
iFlood: A Stable and Effective Regularizer
However, our further studies uncover that the design of the loss function of Flooding can lead to a discrepancy between its objective and implementation, and cause the instability issue.
Towards Automatic Bias Detection in Knowledge Graphs
With the recent surge in social applications relying on knowledge graphs, the need for techniques to ensure fairness in KG based methods is becoming increasingly evident.
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery
In this paper, we propose a Transformer-based decoder and construct a UNet-like Transformer (UNetFormer) for real-time urban scene segmentation.
Ranked #1 on
Scene Segmentation
on UAVid
Evaluating Bayes Error Estimators on Real-World Datasets with FeeBee
The Bayes error rate (BER) is a fundamental concept in machine learning that quantifies the best possible accuracy any classifier can achieve on a fixed probability distribution.
LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis
We show that these DP GCN mechanisms are not always resilient against LinkTeller empirically under mild privacy guarantees ($\varepsilon>5$).
Tackling the Overestimation of Forest Carbon with Deep Learning and Aerial Imagery
This proposal paper describes the first systematic comparison of forest carbon estimation from aerial imagery, satellite imagery, and ground-truth field measurements via deep learning-based algorithms for a tropical reforestation project.
VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition
End-to-end AutoML has attracted intensive interests from both academia and industry, which automatically searches for ML pipelines in a space induced by feature engineering, algorithm/model selection, and hyper-parameter tuning.
BAGUA: Scaling up Distributed Learning with System Relaxations
Recent years have witnessed a growing list of systems for distributed data-parallel training.
Attention-based Neural Network for Driving Environment Complexity Perception
The output from the proposed algorithm is a surrounding environment complexity parameter.
Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks
In particular, we develop KEMLP by integrating a diverse set of weak auxiliary models based on their logical relationships to the main DNN model that performs the target task.
OpenBox: A Generalized Black-box Optimization Service
Black-box optimization (BBO) has a broad range of applications, including automatic machine learning, engineering, physics, and experimental design.
Knowledge Router: Learning Disentangled Representations for Knowledge Graphs
To this end, this paper proposes to learn disentangled representations of KG entities - a new method that disentangles the inner latent properties of KG entities.
TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
Towards Demystifying Serverless Machine Learning Training
The appeal of serverless (FaaS) has triggered a growing interest on how to use it in data-intensive applications such as ETL, query processing, or machine learning (ML).
Multiattention network for semantic segmentation of fine-resolution remote sensing images
A novel attention mechanism of kernel attention with linear complexity is proposed to alleviate the large computational demand in attention.
Ranked #7 on
Semantic Segmentation
on ISPRS Vaihingen
A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images
The fully convolutional network (FCN) with an encoder-decoder architecture has been the standard paradigm for semantic segmentation.
Ranked #3 on
Semantic Segmentation
on ISPRS Potsdam
(using extra training data)
Multilingual Language Models Predict Human Reading Behavior
We analyze if large language models are able to predict patterns of human reading behavior.
Distributed Learning Systems with First-order Methods
Scalable and efficient distributed learning is one of the main driving forces behind the recent rapid advancement of machine learning and artificial intelligence.
TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
In this paper, we aim to explore the power of generative models and gradient sparsity, and propose a scalable privacy-preserving generative model DATALENS.
Scale-aware Neural Network for Semantic Segmentation of Multi-resolution Remote Sensing Images
However, MSR images suffer from two critical issues: 1) increased scale variation of geo-objects and 2) loss of detailed information at coarse spatial resolutions.
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
In this paper, we propose Spectral Temporal Graph Neural Network (StemGNN) to further improve the accuracy of multivariate time-series forecasting.
Evolving Attention with Residual Convolutions
In this paper, we propose a novel and generic mechanism based on evolving attention to improve the performance of transformers.
Decoding EEG Brain Activity for Multi-Modal Natural Language Processing
In this paper, we present the first large-scale study of systematically analyzing the potential of EEG brain activity data for improving natural language processing tasks, with a special focus on which features of the signal are most beneficial.
Switch Spaces: Learning Product Spaces with Sparse Gating
In order for learned representations to be effective and efficient, it is ideal that the geometric inductive bias aligns well with the underlying structure of the data.
A2-FPN for Semantic Segmentation of Fine-Resolution Remotely Sensed Images
Based on FPN and AAM, a novel framework named Attention Aggregation Feature Pyramid Network (A2-FPN) is developed for semantic segmentation of fine-resolution remotely sensed images.
A Data Quality-Driven View of MLOps
Developing machine learning models can be seen as a process similar to the one established for traditional software development.
1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
One of the most effective methods is error-compensated compression, which offers robust convergence speed even under 1-bit compression.
EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery Classification
The proposed CNN model, namely EEG-Inception, is built on the backbone of the Inception-Time network, which showed to be highly efficient and accurate for time-series classification.
Predictive Attention Transformer: Improving Transformer with Attention Map Prediction
Instead, we model their dependencies via a chain of prediction models that take previous attention maps as input to predict the attention maps of a new layer through convolutional neural networks.
Suspicious Massive Registration Detection via Dynamic Heterogeneous Graph Neural Networks
Massive account registration has raised concerns on risk management in e-commerce companies, especially when registration increases rapidly within a short time frame.
Efficient Automatic CASH via Rising Bandits
In this framework, the BO methods are used to solve the HPO problem for each ML algorithm separately, incorporating a much smaller hyperparameter space for BO methods.
MFES-HB: Efficient Hyperband with Multi-Fidelity Quality Measurements
Instead of sampling configurations randomly in HB, BOHB samples configurations based on a BO surrogate model, which is constructed with the high-fidelity measurements only.
CogniVal in Action: An Interface for Customizable Cognitive Word Embedding Evaluation
We demonstrate the functionalities of the new user interface for CogniVal.
Learning to Mutate with Hypergradient Guided Population
Computing the gradient of model hyperparameters, i. e., hypergradient, enables a promising and natural way to solve the hyperparameter optimization task.
Multi-stage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Images
The attention mechanism can refine the extracted feature maps and boost the classification performance of the deep network, which has become an essential technique in computer vision and natural language processing.
xFraud: Explainable Fraud Transaction Detection
At online retail platforms, it is crucial to actively detect the risks of transactions to improve customer experience and minimize financial loss.
Robust Unsupervised Small Area Change Detection from SAR Imagery Using Deep Learning
In this paper, a robust unsupervised approach is proposed for small area change detection from multi-temporal SAR images using deep learning.
Learning User Representations with Hypercuboids for Recommender Systems
Furthermore, we present two variants of hypercuboids to enhance the capability in capturing the diversities of user interests.
Online Active Model Selection for Pre-trained Classifiers
Given $k$ pre-trained classifiers and a stream of unlabeled data examples, how can we actively decide when to query a label so that we can distinguish the best model from the rest while making a small number of queries?
Automatic Feasibility Study via Data Quality Analysis for ML: A Case-Study on Label Noise
In our experience of working with domain experts who are using today's AutoML systems, a common problem we encountered is what we call "unrealistic expectations" -- when users are facing a very challenging task with a noisy data acquisition process, while being expected to achieve startlingly high accuracy with machine learning (ML).
On Convergence of Nearest Neighbor Classifiers over Feature Transformations
This analysis requires in-depth understanding of the properties that connect both the transformed space and the raw feature space.
Which Model to Transfer? Finding the Needle in the Growing Haystack
Transfer learning has been recently popularized as a data-efficient alternative to training models from scratch, in particular for computer vision tasks where it provides a remarkably solid baseline.
MicroRec: Efficient Recommendation Inference by Hardware and Data Structure Solutions
MicroRec accelerates recommendation inference by (1) redesigning the data structures involved in the embeddings to reduce the number of lookups needed and (2) taking advantage of the availability of High-Bandwidth Memory (HBM) in FPGA accelerators to tackle the latency by enabling parallel lookups.
Optimal Provable Robustness of Quantum Classification via Quantum Hypothesis Testing
This link leads to a tight robustness condition which puts constraints on the amount of noise a classifier can tolerate, independent of whether the noise source is natural or adversarial.
A Principled Approach to Data Valuation for Federated Learning
The federated SV preserves the desirable properties of the canonical SV while it can be calculated without incurring extra communication cost and is also able to capture the effect of participation order on data value.
Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Images
A novel attention mechanism of kernel attention with linear complexity is proposed to alleviate the large computational demand in attention.
APMSqueeze: A Communication Efficient Adam-Preconditioned Momentum SGD Algorithm
Adam is the important optimization algorithm to guarantee efficiency and accuracy for training many important tasks such as BERT and ImageNet.
A Survey and Tutorial of EEG-Based Brain Monitoring for Driver State Analysis
Then, the EEG signal preprocessing, feature extraction, and classification algorithms for driver state detection are reviewed.
A Computationally Efficient Multiclass Time-Frequency Common Spatial Pattern Analysis on EEG Motor Imagery
The experiment results show the proposed algorithm average computation time is 37. 22% less than the FBCSP (1st winner in the BCI Competition IV) and 4. 98% longer than the conventional CSP method.
Land Cover Classification from Remote Sensing Images Based on Multi-Scale Fully Convolutional Network
In this paper, a Multi-Scale Fully Convolutional Network (MSFCN) with multi-scale convolutional kernel is proposed to exploit discriminative representations from two-dimensional (2D) satellite images.
FIVES: Feature Interaction Via Edge Search for Large-Scale Tabular Data
Then we instantiate this search strategy by optimizing both a dedicated graph neural network (GNN) and the adjacency tensor associated with the defined feature graph.
MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Images
In this Letter, we incorporate multi-scale features generated by different layers of U-Net and design a multi-scale skip connected and asymmetric-convolution-based U-Net (MACU-Net), for segmentation using fine-resolution remotely sensed images.
Adversarial Learning for Debiasing Knowledge Graph Embeddings
As a second step, we explore gender bias in KGE, and a careful examination of popular KGE algorithms suggest that sensitive attribute like the gender of a person can be predicted from the embedding.
Nearest Neighbor Classifiers over Incomplete Information: From Certain Answers to Certain Predictions
Machine learning (ML) applications have been thriving recently, largely attributed to the increasing availability of data.
Control, Generate, Augment: A Scalable Framework for Multi-Attribute Text Generation
We introduce CGA, a conditional VAE architecture, to control, generate, and augment text.
TrueBranch: Metric Learning-based Verification of Forest Conservation Projects
Recent works propose low-cost and accurate MRV via automatically determining forest carbon from drone imagery, collected by the landowners.
RAB: Provable Robustness Against Backdoor Attacks
In addition, we theoretically show that it is possible to train the robust smoothed models efficiently for simple models such as K-nearest neighbor classifiers, and we propose an exact smooth-training algorithm that eliminates the need to sample from a noise distribution for such models.
A Robust Imbalanced SAR Image Change Detection Approach Based on Deep Difference Image and PCANet
Parallel FCM are utilized on these two mapped DDIs to obtain three types of pseudo-label pixels, namely, changed pixels, unchanged pixels, and intermediate pixels.
Improving Certified Robustness via Statistical Learning with Logical Reasoning
Intensive algorithmic efforts have been made to enable the rapid improvements of certificated robustness for complex ML models recently.
TSS: Transformation-Specific Smoothing for Robustness Certification
Moreover, to the best of our knowledge, TSS is the first approach that achieves nontrivial certified robustness on the large-scale ImageNet dataset.
Two-Phase Object-Based Deep Learning for Multi-temporal SAR Image Change Detection
The prediction of this Phase is the set of changed and unchanged superpixels.
TextNAS: A Neural Architecture Search Space tailored for Text Representation
Learning text representation is crucial for text classification and other language related tasks.
Data Science through the looking glass and what we found there
The recent success of machine learning (ML) has led to an explosive growth both in terms of new systems and algorithms built in industry and academia, and new applications built by an ever-growing community of data science (DS) practitioners.
Support Vector Machine Classifier via $L_{0/1}$ Soft-Margin Loss
To distinguish all of them, in this paper, we introduce a new model equipped with an $L_{0/1}$ soft-margin loss (dubbed as $L_{0/1}$-SVM) which well captures the nature of the binary classification.
ZuCo 2.0: A Dataset of Physiological Recordings During Natural Reading and Annotation
We recorded and preprocessed ZuCo 2. 0, a new dataset of simultaneous eye-tracking and electroencephalography during natural reading and during annotation.
Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
Quantifying the importance of each training point to a learning task is a fundamental problem in machine learning and the estimated importance scores have been leveraged to guide a range of data workflows such as data summarization and domain adaption.
DocParser: Hierarchical Structure Parsing of Document Renderings
Translating renderings (e. g. PDFs, scans) into hierarchical document structures is extensively demanded in the daily routines of many real-world applications.
DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition
Despite the wide application of Graph Convolutional Network (GCN), one major limitation is that it does not benefit from the increasing depth and suffers from the oversmoothing problem.
Observer Dependent Lossy Image Compression
To that end, we use a family of loss functions that allows to optimize deep image compression depending on the observer and to interpolate between human perceived visual quality and classification accuracy, enabling a more unified view on image compression.
An Empirical and Comparative Analysis of Data Valuation with Scalable Algorithms
Existing approximation algorithms, although achieving great improvement over the exact algorithm, relies on retraining models for multiple times, thus remaining limited when applied to larger-scale learning tasks and real-world datasets.
CogniVal: A Framework for Cognitive Word Embedding Evaluation
An interesting method of evaluating word representations is by how much they reflect the semantic representations in the human brain.
Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms
The most surprising result is that for unweighted $K$NN classifiers and regressors, the Shapley value of all $N$ data points can be computed, exactly, in $O(N\log N)$ time -- an exponential improvement on computational complexity!
$\texttt{DeepSqueeze}$: Decentralization Meets Error-Compensated Compression
Since the \emph{decentralized} training has been witnessed to be superior to the traditional \emph{centralized} training in the communication restricted scenario, therefore a natural question to ask is "how to apply the error-compensated technology to the decentralized learning to further reduce the communication cost."
DL2: Training and Querying Neural Networks with Logic
We present DL2, a system for training and querying neural networks with logical constraints.
CleanML: A Study for Evaluating the Impact of Data Cleaning on ML Classification Tasks
Data quality affects machine learning (ML) model performances, and data scientists spend considerable amount of time on data cleaning before model training.
Advancing NLP with Cognitive Language Processing Signals
Cognitive language processing data such as eye-tracking features have shown improvements on single NLP tasks.
MLSys: The New Frontier of Machine Learning Systems
Machine learning (ML) techniques are enjoying rapidly increasing adoption.
Sensing Social Media Signals for Cryptocurrency News
The ability to track and monitor relevant and important news in real-time is of crucial interest in multiple industrial sectors.
Accelerating Generalized Linear Models with MLWeaving: A One-Size-Fits-All System for Any-precision Learning (Technical Report)
Learning from the data stored in a database is an important function increasingly available in relational engines.
Continuous Integration of Machine Learning Models with ease.ml/ci: Towards a Rigorous Yet Practical Treatment
Continuous integration is an indispensable step of modern software engineering practices to systematically manage the life cycles of system development.
Towards Efficient Data Valuation Based on the Shapley Value
In this paper, we study the problem of data valuation by utilizing the Shapley value, a popular notion of value which originated in cooperative game theory.
Entity Recognition at First Sight: Improving NER with Eye Movement Information
Previous research shows that eye-tracking data contains information about the lexical and syntactic properties of text, which can be used to improve natural language processing models.
Exploring galaxy evolution with generative models
Methods: By learning a latent space representation of the data, we can use this network to forward model and explore hypotheses in a data-driven way.
Distributed Learning over Unreliable Networks
Most of today's distributed machine learning systems assume {\em reliable networks}: whenever two machines exchange information (e. g., gradients or models), the network should guarantee the delivery of the message.
Patient Risk Assessment and Warning Symptom Detection Using Deep Attention-Based Neural Networks
In addition, a method to detect warning symptoms is implemented to render the classification task transparent from a medical perspective.
$D^2$: Decentralized Training over Decentralized Data
While training a machine learning model using multiple workers, each of which collects data from its own data source, it would be useful when the data collected from different workers are unique and different.
Ranked #3 on
Multi-view Subspace Clustering
on ORL
Using transfer learning to detect galaxy mergers
We investigate the use of deep convolutional neural networks (deep CNNs) for automatic visual detection of galaxy mergers.
ETH-DS3Lab at SemEval-2018 Task 7: Effectively Combining Recurrent and Convolutional Neural Networks for Relation Classification and Extraction
Reliably detecting relevant relations between entities in unstructured text is a valuable resource for knowledge extraction, which is why it has awaken significant interest in the field of Natural Language Processing.
PSFGAN: a generative adversarial network system for separating quasar point sources and host galaxy light
We test the method using Sloan Digital Sky Survey (SDSS) r-band images with artificial AGN point sources added which are then removed using the GAN and with parametric methods using GALFIT.
Astrophysics of Galaxies Data Analysis, Statistics and Probability
D$^2$: Decentralized Training over Decentralized Data
While training a machine learning model using multiple workers, each of which collects data from their own data sources, it would be most useful when the data collected from different workers can be {\em unique} and {\em different}.
Communication Compression for Decentralized Training
In this paper, We explore a natural question: {\em can the combination of both techniques lead to a system that is robust to both bandwidth and latency?}
AutoML from Service Provider's Perspective: Multi-device, Multi-tenant Model Selection with GP-EI
In this paper, we focus on the AutoML problem from the \emph{service provider's perspective}, motivated by the following practical consideration: When an AutoML service needs to serve {\em multiple users} with {\em multiple devices} at the same time, how can we allocate these devices to users in an efficient way?
Compressive Sensing Using Iterative Hard Thresholding with Low Precision Data Representation: Theory and Applications
Modern scientific instruments produce vast amounts of data, which can overwhelm the processing ability of computer systems.
DataBright: Towards a Global Exchange for Decentralized Data Ownership and Trusted Computation
We illustrate that trusted computation can enable the creation of an AI market, where each data point has an exact value that should be paid to its creator.
Asynchronous Decentralized Parallel Stochastic Gradient Descent
Can we design an algorithm that is robust in a heterogeneous environment, while being communication efficient and maintaining the best-possible convergence rate?
Ease.ml: Towards Multi-tenant Resource Sharing for Machine Learning Workloads
We ask, as a "service provider" that manages a shared cluster of machines among all our users running machine learning workloads, what is the resource allocation strategy that maximizes the global satisfaction of all our users?
ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning
We examine training at reduced precision, both from a theoretical and practical perspective, and ask: is it possible to train models at end-to-end low precision with provable guarantees?
MLBench: How Good Are Machine Learning Clouds for Binary Classification Tasks on Structured Data?
We then compare the performance of the top winning code available from Kaggle with that of running machine learning clouds from both Azure and Amazon on mlbench.
Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent
On network configurations with low bandwidth or high latency, D-PSGD can be up to one order of magnitude faster than its well-optimized centralized counterparts.
Layerwise Systematic Scan: Deep Boltzmann Machines and Beyond
For Markov chain Monte Carlo methods, one of the greatest discrepancies between theory and system is the scan order - while most theoretical development on the mixing time analysis deals with random updates, real-world systems are implemented with systematic scans.
Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
Observations of astrophysical objects such as galaxies are limited by various sources of random and systematic noise from the sky background, the optical system of the telescope and the detector used to record the data.
The ZipML Framework for Training Models with End-to-End Low Precision: The Cans, the Cannots, and a Little Bit of Deep Learning
When applied to linear models together with double sampling, we save up to another 1. 7x in data movement compared with uniform quantization.
Omnivore: An Optimizer for Multi-device Deep Learning on CPUs and GPUs
Given a specification of a convolutional neural network, our goal is to minimize the time to train this model on a cluster of commodity CPUs and GPUs.
CYCLADES: Conflict-free Asynchronous Machine Learning
We present CYCLADES, a general framework for parallelizing stochastic optimization algorithms in a shared memory setting.
Asynchrony begets Momentum, with an Application to Deep Learning
Since asynchronous methods have better hardware efficiency, this result may shed light on when asynchronous execution is more efficient for deep learning systems.
Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms
Stochastic gradient descent (SGD) is a ubiquitous algorithm for a variety of machine learning problems.
Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width
Gibbs sampling on factor graphs is a widely used inference technique, which often produces good empirical results.
Building a Large-scale Multimodal Knowledge Base System for Answering Visual Queries
The complexity of the visual world creates significant challenges for comprehensive visual understanding.
Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithms
with relaxed assumptions on the sparsity of the problem; (2) we analyze asynchronous SGD algorithms for non-convex matrix problems including matrix completion; and (3) we design and analyze an asynchronous SGD algorithm, called Buckwild!, that uses lower-precision arithmetic.
Caffe con Troll: Shallow Ideas to Speed Up Deep Learning
We present Caffe con Troll (CcT), a fully compatible end-to-end version of the popular framework Caffe with rebuilt internals.
Incremental Knowledge Base Construction Using DeepDive
Populating a database with unstructured information is a long-standing problem in industry and research that encompasses problems of extraction, cleaning, and integration.
Parallel Feature Selection Inspired by Group Testing
Superior performance of our method is demonstrated on a challenging relation extraction task from a very large data set that have both redundant features and sample size in the order of millions.
Feature Engineering for Knowledge Base Construction
Our approach to KBC is based on joint probabilistic inference and learning, but we do not see inference as either a panacea or a magic bullet: inference is a tool that allows us to be systematic in how we construct, debug, and improve the quality of such systems.
A machine-compiled macroevolutionary history of Phanerozoic life
Many aspects of macroevolutionary theory and our understanding of biotic responses to global environmental change derive from literature-based compilations of palaeontological data.
DimmWitted: A Study of Main-Memory Statistical Analytics
We perform the first study of the tradeoff space of access methods and replication to support statistical analytics using first-order methods executed in the main memory of a Non-Uniform Memory Access (NUMA) machine.
An Approximate, Efficient LP Solver for LP Rounding
Many problems in machine learning can be solved by rounding the solution of an appropriate linear program.
