Publication Type: Conference proceedings

PGHash: Large-Scale Distributed Learning via Private On-Device Locally Sensitive Hashing

Sparsity in Neural Networks 2023 workshop, ICLR 2023.
Tahseen Rabbani, Marco Bornstein, Furong Huang
Publisher's website

Learning Unforeseen Robustness from Out-of-distribution Data Using Equivariant Domain Translator

ICLR 2023 Workshop on Trustworthy ML, ICLR 2023.
Sicheng Zhu, Bang An, Furong Huang, Sanghyun Hong
Publisher's website

Where do Models go Wrong? Parameter-Space Saliency Maps for Explainabilit

Neural Information Processing System (NeurIPS), 2022.
Roman Levin, Manli Shu, Eitan Borgnia, Furong Huang, Micah Goldblum, Tom Goldstein
Publisher's website

End-to-end Scalable Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking

Neural Information Processing System (NeurIPS), 2022.
Arpit Bansal, Avi Schwarzschild, Eitan Borgnia, Zeyad Emam, Furong Huang, Micah Goldblum, Tom Goldstein
Publisher's website

Adversarial Auto- Augment with Label Preservation: A Representation Learning Principle Guided Approach

Neural Information Processing System (NeurIPS), 2022.
Kaiwen Yang, Yanchao Sun, Jiahao Su, Fengxiang He, Xinmei Tian, Furong Huang, Tianyi Zhou, Dacheng Tao
Publisher's website

Sketch-GNN: Efficient GNNs with Graph Size-Independent Scalability

Neural Information Processing System (NeurIPS), 2022.
Mucong Ding, Tahseen Rabbani, Bang An, Evan Wang, Furong Huang
Publisher's website

Transferring Fairness under Distribution Shifts via Fair Consistency Regularization

Neural Information Processing System (NeurIPS), 2022.
Bang An, Zora Che, Mucong Ding, Furong Huang
Publisher's website

Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning

Neural Information Processing System (NeurIPS), 2022.
Yongyuan Liang, Yanchao Sun, Ruijie Zheng, Furong Huang
Publisher's website

Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework

International Conference on Machine Learning (ICML), 2022.
Jiahao Su, Wonmin Byeon, Furong Huang
Publisher's website

Tuformer: Data-driven Design of Transformers for Improved Generalization or Efficiency

The Tenth International Conference on Learning Representations (ICLR), 2022.
Xiaoyu Liu, Jiahao Su, Furong Huang
Publisher's website