Robustness

Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation EMNLP 2021 Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection ACL 2021 On Robustness and Transferability of Convolutional Neural Networks CVPR 2021 On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise EMNLP 2021 Power up! Robust Graph Convolutional Network via Graph Powering AAAI 2021 Quality-Agnostic Image Recognition via Invertible Decoder CVPR 2021 Robust Domain Randomised Reinforcement Learning through Peer-to-Peer Distillation ACML 2021 Simpler Certified Radius Maximization by Propagating Covariances CVPR 2021 Sometimes We Want Ungrammatical Translations EMNLP 2021 Sorting through the noise: Testing robustness of information processing in pre-trained language models EMNLP 2021 Towards Robustness Against Natural Language Word Substitutions ICLR 2021 Towards Robustness of Text-to-SQL Models against Synonym Substitution ACL 2021 Understanding Model Robustness to User-generated Noisy Texts EMNLP 2021 Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations CVPR 2020 Benchmarking the Robustness of Semantic Segmentation Models CVPR 2020 Can gradient clipping mitigate label noise? ICLR 2020 Fairness for Robust Log Loss Classification AAAI 2020 Fine-Tuning MT systems for Robustness to Second-Language Speaker Variations EMNLP 2020 GNNGuard: Defending Graph Neural Networks against Adversarial Attacks NeurIPS 2020 Improving robustness against common corruptions by covariate shift adaptation NeurIPS 2020 Leakage-Robust Classifier via Mask-Enhanced Training (Student Abstract) AAAI 2020 Lipschitz-Certifiable Training with a Tight Outer Bound NeurIPS 2020 Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness NeurIPS 2020 On the Trade-off between Adversarial and Backdoor Robustness NeurIPS 2020 Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020