Robust Learning

Robust learning aims to develop machine learning models that are resilient to various forms of noise and uncertainty in data, including label noise, adversarial attacks, and distribution shifts. Current research focuses on developing algorithms and model architectures (e.g., multiview SVMs, graph neural networks, and diffusion models) that incorporate techniques like adversarial training, data augmentation, and loss function modifications to enhance robustness. These advancements are crucial for improving the reliability and generalizability of machine learning models in real-world applications, particularly in safety-critical domains like healthcare and autonomous systems, where data imperfections are common.

Papers

August 27, 2022

Overparameterization from Computational Constraints
Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Mingyuan Wang
Large Model Robust Learning Information Theoretic Robust Model Overparametrization Bound Resource Constraint Computational Account

August 26, 2022

Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training
Zihui Wu, Haichang Gao, Bingqian Zhou, Xiaoyan Guo, Shudong Zhang
Adversarial Training Adversarial Robustness Robust Learning Low Complexity Better Robustness Bregman Divergence

August 24, 2022

Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization
Qi Wei, Haoliang Sun, Xiankai Lu, Yilong Yin
Loss Function Label Noise Generalization Performance Robust Learning Selection Bias Noisy Sample Small Loss

August 23, 2022

Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling
Boshen Zhang, Yuxi Li, Yuanpeng Tu, Jinlong Peng, Yabiao Wang, Cunlin Wu, Yang Xiao, Cairong Zhao
LeArning Abstract Noisy Label Robust Learning Noisy Data Credibility Assessment Small Loss

August 17, 2022

Two Heads are Better than One: Robust Learning Meets Multi-branch Models
Dong Huang, Qingwen Bu, Yuhao Qing, Haowen Pi, Sen Wang, Heming Cui
Adversarial Attack Adversarial Example Adversarial Training Adversarial Robustness Robust Learning Human Head Dual Branch

August 10, 2022

Robust Methods for High-Dimensional Linear Learning
Ibrahim Merad, Stéphane Gaïffas
High Dimensional Robust Learning Robust Method Batch Learning Low Rank Matrix Recovery

August 5, 2022

Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls
Da Ju, Jing Xu, Y-Lan Boureau, Jason Weston
LeArning Abstract Native Robustness Raw Data Conversational Agent Robust Learning Adversarial Behavior Adversarial Scenario Troll Meme Adversarial Response

August 3, 2022

Robust Learning of Deep Time Series Anomaly Detection Models with Contaminated Training Data
Wenkai Li, Cheng Feng, Ting Chen, Jun Zhu
Training Data Robust Learning Deep Learning Based Deep Anomaly Detection

July 16, 2022

MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks
Ali Ramezani-Kebrya, Iman Tabrizian, Fartash Faghri, Petar Popovski
Robust Learning Byzantine Robust Adversarial Agent Aggregated Gradient Byzantine Robust Aggregation Targeted Attack

June 27, 2022

Towards Harnessing Feature Embedding for Robust Learning with Noisy Labels
Chuang Zhang, Li Shen, Jian Yang, Chen Gong
Noisy Label Label Noise Robust Learning Harnessing Data LabEl Noise

June 20, 2022

Understanding Robust Learning through the Lens of Representation Similarities
Christian Cianfarani, Arjun Nitin Bhagoji, Vikash Sehwag, Ben Y. Zhao, Prateek Mittal, Haitao Zheng
Representation Learning Camera Lens Robust Learning Robust Representation Robust Training Similar Representation Robust Network DNN Robustness

June 14, 2022

ABCinML: Anticipatory Bias Correction in Machine Learning Applications
Abdulaziz A. Almuzaini, Chidansh A. Bhatt, David M. Pennock, Vivek K. Singh
Algorithmic Fairness Robust Learning Machine Learning Application Dynamic Learning Bias Correction

June 9, 2022

Trimmed Maximum Likelihood Estimation for Robust Learning in Generalized Linear Models
Pranjal Awasthi, Abhimanyu Das, Weihao Kong, Rajat Sen
Robust Learning Generalized Linear Model Adversarial Corruption Gaussian Approximation Label Corruption General Linear Corruption Process

June 4, 2022

Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation
Haohan Wang, Zeyi Huang, Xindi Wu, Eric P. Xing
Data Augmentation Robust Learning Invariant Representation L2 Regularization Alignment Regularization

May 31, 2022

Strategic Classification with Graph Neural Networks
Itay Eilat, Ben Finkelshtein, Chaim Baskin, Nir Rosenfeld
Graph Neural Network Graph Classification Robust Learning User Intent Strategic Classification

May 28, 2022

Visual Superordinate Abstraction for Robust Concept Learning
Qi Zheng, Chaoyue Wang, Dadong Wang, Dacheng Tao
Visual Representation Robust Learning Visual Concept Concept Learning Semantic Subspace Visual Abstraction

May 26, 2022

An Analytic Framework for Robust Training of Artificial Neural Networks
Ramin Barati, Reza Safabakhsh, Mohammad Rahmati
Neural Network Adversarial Attack Adversarial Example Robust Learning Robust Model Robust Training

May 15, 2022

Meta Self-Refinement for Robust Learning with Weak Supervision
Dawei Zhu, Xiaoyu Shen, Michael A. Hedderich, Dietrich Klakow
Pseudo Label Label Noise Weak Supervision Robust Learning Noise Robust Learning Self Refinement Meta Gradient

May 12, 2022

Sample Complexity Bounds for Robustly Learning Decision Lists against Evasion Attacks
Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska, James Worrell
Sample Complexity Robust Learning Evasion Attack PAC Learning Sample Complexity Bound

May 10, 2022

StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random
Haoxuan Li, Chunyuan Zheng, Peng Wu
Raw Data Recommender System Effective Recommendation Robust Learning Imputation Algorithm Random Participation Double Robustness