Robust Training

Robust training aims to develop machine learning models that are resilient to various forms of noise and uncertainty, including data imperfections, adversarial attacks, and distribution shifts. Current research focuses on improving model robustness across diverse applications and data types, employing techniques like adversarial training, data augmentation strategies (e.g., Mixup, diffusion-based variations), and novel loss functions that incorporate noise governance or margin maximization. These advancements are crucial for deploying reliable and trustworthy AI systems in real-world scenarios, particularly in safety-critical applications where model performance under uncertainty is paramount.

Papers

March 28, 2022

Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC
Xiang An, Jiankang Deng, Jia Guo, Ziyong Feng, Xuhan Zhu, Jing Yang, Tongliang Liu
Face Recognition Robust Training Deep Face Recognition Training Datasets Fully Connected Layer STONE Deterioration Pattern Discriminative Embeddings Margin Softmax

March 16, 2022

On the Convergence of Certified Robust Training with Interval Bound Propagation
Yihan Wang, Zhouxing Shi, Quanquan Gu, Cho-Jui Hsieh
Gradient Descent Adversarial Perturbation Early Stage Convergence Robust Training Interval Bound Propagation

February 28, 2022

Robust Training under Label Noise by Over-parameterization
Sheng Liu, Zhihui Zhu, Qing Qu, Chong You
Neural Network Label Noise Robust Training Parameterized Model Benign Over Parameterization

February 18, 2022

Exploring Adversarially Robust Training for Unsupervised Domain Adaptation
Shao-Yuan Lo, Vishal M. Patel
Adversarial Attack Domain Adaptation Adversarial Training Adversarial Robustness Robust Training Robust Adversarial Training

February 2, 2022

Robust Training of Neural Networks Using Scale Invariant Architectures
Zhiyuan Li, Srinadh Bhojanapalli, Manzil Zaheer, Sashank J. Reddi, Sanjiv Kumar
Large Language Model Neural Network Stochastic Gradient Descent Robust Training Scale Invariant Memory Efficient Training Vanilla Gradient Descent

January 29, 2022

Investigating Why Contrastive Learning Benefits Robustness Against Label Noise
Yihao Xue, Kyle Whitecross, Baharan Mirzasoleiman
Contrastive Learning Native Robustness Label Noise Robust Training

January 28, 2022

REET: Robustness Evaluation and Enhancement Toolbox for Computational Pathology
Alex Foote, Amina Asif, Nasir Rajpoot, Fayyaz Minhas
Computational Pathology Feature Enhancement Robust Training Robustness Evaluation Domain Robustness Computational Pathology CPath

January 15, 2022

Concise Logarithmic Loss Function for Robust Training of Anomaly Detection Model
YeongHyeon Park
Loss Function Robust Training Based Anomaly Detection Mean Squared Error

December 1, 2021

Training Experimentally Robust and Interpretable Binarized Regression Models Using Mixed-Integer Programming
Sanjana Tule, Nhi Ha Lan Le, Buser Say
Mixed Integer Logistic Regression Robust Training Multi Class Classification Task Model Regularization

November 19, 2021

Fooling Adversarial Training with Inducing Noise
Zhirui Wang, Yifei Wang, Yisen Wang
Adversarial Attack Native Robustness Adversarial Training Industrial Disturbing Noise Model Robustness Robust Training

November 12, 2021

Adversarially Robust Learning for Security-Constrained Optimal Power Flow
Priya L. Donti, Aayushya Agarwal, Neeraj Vijay Bedmutha, Larry Pileggi, J. Zico Kolter
Robust Learning Robust Training Optimal Power Flow Minimax Optimization Problem