Shengyuan Hu

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 14

Top Topics

Learning Problems

Top Venues

Publications

Shengyuan Hu, Yiwei Fu, Zhiwei Steven Wu, Virginia Smith
Jogging the Memory of Unlearned Model Through Targeted Relearning Attack. CoRR (2024)
Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith
Fair Federated Learning via Bounded Group Loss. SaTML (2024)
Shengyuan Hu, Saeed Mahloujifar, Virginia Smith, Kamalika Chaudhuri, Chuan Guo
Privacy Amplification for the Gaussian Mechanism via Bounded Support. CoRR (2024)
Qi Pang, Shengyuan Hu, Wenting Zheng, Virginia Smith
Attacking LLM Watermarks by Exploiting Their Strengths. CoRR (2024)
Shengyuan Hu, Dung Daniel T. Ngo, Shuran Zheng, Virginia Smith, Zhiwei Steven Wu
Federated Learning as a Network Effects Game. CoRR (2023)
Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith
Provably Fair Federated Learning via Bounded Group Loss. CoRR (2022)
Ken Ziyu Liu, Shengyuan Hu, Steven Wu, Virginia Smith
On Privacy and Personalization in Cross-Silo Federated Learning. NeurIPS (2022)
Ziyu Liu, Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith
On Privacy and Personalization in Cross-Silo Federated Learning. CoRR (2022)
Shengyuan Hu, Jack Goetz, Kshitiz Malik, Hongyuan Zhan, Zhe Liu, Yue Liu
FedSynth: Gradient Compression via Synthetic Data in Federated Learning. CoRR (2022)
Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith
Private Multi-Task Learning: Formulation and Applications to Federated Learning. CoRR (2021)
Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith
Ditto: Fair and Robust Federated Learning Through Personalization. ICML (2021)
Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith
Federated Multi-Task Learning for Competing Constraints. CoRR (2020)
Shengyuan Hu, Tao Yu, Chuan Guo, Wei-Lun Chao, Kilian Q. Weinberger
A New Defense Against Adversarial Images: Turning a Weakness into a Strength. NeurIPS (2019)
Tao Yu, Shengyuan Hu, Chuan Guo, Wei-Lun Chao, Kilian Q. Weinberger
A New Defense Against Adversarial Images: Turning a Weakness into a Strength. CoRR (2019)