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

March 15, 2024

Conformal Predictions for Probabilistically Robust Scalable Machine Learning Classification
Alberto Carlevaro, Teodoro Alamo Cantarero, Fabrizio Dabbene, Maurizio Mongelli
Machine Learning Conformal Prediction Robust Learning Reliable Learning

March 13, 2024

An Adaptive Cost-Sensitive Learning and Recursive Denoising Framework for Imbalanced SVM Classification
Lu Jiang, Qi Wang, Yuhang Chang, Jianing Song, Haoyue Fu, Xiaochun Yang
Robust Learning Imbalanced Classification Cost Sensitive Iterative Denoising

March 4, 2024

Mitigating Label Noise on Graph via Topological Sample Selection
Yuhao Wu, Jiangchao Yao, Xiaobo Xia, Jun Yu, Ruxin Wang, Bo Han, Tongliang Liu
Graph Drawing Label Noise Robust Learning Topological Information Topological Metric Non IID Data Informative Sampling

February 22, 2024

Structure-agnostic Optimality of Doubly Robust Learning for Treatment Effect Estimation
Jikai Jin, Vasilis Syrgkanis
Causal Inference Treatment Effect Robust Learning Robust Estimation Average Treatment Effect

February 12, 2024

February 5, 2024

A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning
Abdelhakim Benechehab, Albert Thomas, Giuseppe Paolo, Maurizio Filippone, Balázs Kégl
Loss Function Model Based Reinforcement Learning Robust Learning Multi Step Batch Reinforcement Learning

December 26, 2023

Robust Neural Pruning with Gradient Sampling Optimization for Residual Neural Networks
Juyoung Yun
Natural Gradient Gradient Based Robust Learning Residual Neural Network Efficient Neural Network

December 20, 2023

Robust Loss Functions for Training Decision Trees with Noisy Labels
Jonathan Wilton, Nan Ye
Loss Function Decision Tree Noisy Label Robust Learning Adaptive Loss Robust Loss Function

December 14, 2023

Towards Inductive Robustness: Distilling and Fostering Wave-induced Resonance in Transductive GCNs Against Graph Adversarial Attacks
Ao Liu, Wenshan Li, Tao Li, Beibei Li, Hanyuan Huang, Pan Zhou
Robust Learning Graph Adversarial Attack Acoustic Resonance

December 1, 2023

Adaptive Robust Learning using Latent Bernoulli Variables
Aleksandr Karakulev, Dave Zachariah, Prashant Singh
Variational Inference Robust Learning Robust Learning Method

November 14, 2023

Robust Learning Based Condition Diagnosis Method for Distribution Network Switchgear
Wenxi Zhang, Zhe Li, Weixi Li, Weisi Ma, Xinyi Chen, Sizhe Li
Robust Learning Feature Vector Distribution System Self Supervised Loss Learning Based Method Feature Mapping

October 31, 2023

October 24, 2023

Robust Learning via Conditional Prevalence Adjustment
Minh Nguyen, Alan Q. Wang, Heejong Kim, Mert R. Sabuncu
Robust Learning Causal Prediction Association Capability Generating Process

October 16, 2023

Proper Laplacian Representation Learning
Diego Gomez, Michael Bowling, Marlos C. Machado
Robust Learning Graph Laplacian Large Scale Reinforcement Learning Laplacian Representation

October 12, 2023

Provably Robust Cost-Sensitive Learning via Randomized Smoothing
Yuan Xin, Michael Backes, Xiao Zhang
Adversarial Perturbation Robust Learning Randomized Smoothing Robustness Certification Cost Sensitive

October 9, 2023

HydraViT: Adaptive Multi-Branch Transformer for Multi-Label Disease Classification from Chest X-ray Images
Şaban Öztürk, M. Yiğit Turalı, Tolga Çukur
Convolutional Neural Network Multi Label Chest X Ray Robust Learning Chest X Ray Image X Ray Image Branch Transformer

September 22, 2023

Robotic Handling of Compliant Food Objects by Robust Learning from Demonstration
Ekrem Misimi, Alexander Olofsson, Aleksander Eilertsen, Elling Ruud Øye, John Reidar Mathiassen
Robotic Manipulation Robot Learning Robotic Grasping Robust Learning Textual Demonstration

September 14, 2023

Physics-constrained robust learning of open-form partial differential equations from limited and noisy data
Mengge Du, Yuntian Chen, Longfeng Nie, Siyu Lou, Dongxiao Zhang
Nonlinear Dynamic Robust Learning Noisy Data Governing Equation

Robust Learning

Papers

Conformal Predictions for Probabilistically Robust Scalable Machine Learning Classification

An Adaptive Cost-Sensitive Learning and Recursive Denoising Framework for Imbalanced SVM Classification

Mitigating Label Noise on Graph via Topological Sample Selection

Structure-agnostic Optimality of Doubly Robust Learning for Treatment Effect Estimation

Multi-Attribute Vision Transformers are Efficient and Robust Learners

Strategically-Robust Learning Algorithms for Bidding in First-Price Auctions

A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning

Robust Neural Pruning with Gradient Sampling Optimization for Residual Neural Networks

Robust Loss Functions for Training Decision Trees with Noisy Labels

Towards Inductive Robustness: Distilling and Fostering Wave-induced Resonance in Transductive GCNs Against Graph Adversarial Attacks

Adaptive Robust Learning using Latent Bernoulli Variables

Robust Learning Based Condition Diagnosis Method for Distribution Network Switchgear

Bandit-Driven Batch Selection for Robust Learning under Label Noise

Robust Learning for Smoothed Online Convex Optimization with Feedback Delay

Robust Learning via Conditional Prevalence Adjustment

Proper Laplacian Representation Learning

Provably Robust Cost-Sensitive Learning via Randomized Smoothing

HydraViT: Adaptive Multi-Branch Transformer for Multi-Label Disease Classification from Chest X-ray Images

Robotic Handling of Compliant Food Objects by Robust Learning from Demonstration

Physics-constrained robust learning of open-form partial differential equations from limited and noisy data