Xiaoyang Wang

I’m a Ph.D. student at the University of Illinois at Urbana-Champaign, collaborating with Prof. Klara Nahrstedt, Prof. Sanmi Koyejo, and FedML.

I study machine learning, focusing on (1) building trustworthy learning systems that perform well across heterogeneous environments and (2) designing efficient data-feedback loops that help explore new environments. I’m also interested in high-performance computing.

Publications

AISTATS 2024

Invariant Aggregator for Defending against Federated Backdoor Attacks

Xiaoyang Wang, Dimitrios Dimitriadis, Sanmi Koyejo, Shruti Tople

ICC 2024

FedCore: Straggler-Free Federated Learning with Distributed Coresets

Hongpeng Guo, Haotian Gu, Xiaoyang Wang, Bo Chen, Eun Kyung Lee, Tamar Eilam, Deming Chen, Klara Nahrstedt

TMLR 2024

Personalized Federated Learning with Spurious Features: An Adversarial Approach

Xiaoyang Wang, Han Zhao, Klara Nahrstedt, Sanmi Koyejo

Middleware 2022

BoFL: Bayesian Optimized Local Training Pace Control for Energy Efficient Federated Learning

Hongpeng Guo, Haotian Gu, Zhe Yang, Xiaoyang Wang, Eun Kyung Lee, Nandhini Chandramoorthy, Tamar Eilam, Deming Chen, Klara Nahrstedt

CLeaR 2022

Identifying Coarse-grained Independent Causal Mechanisms with Self-supervision

Xiaoyang Wang, Klara Nahrstedt, Sanmi Koyejo

arXiv 2020

FedML: A Research Library and Benchmark for Federated Machine Learning

Chaoyang He, Songze Li, Jinhyun So, Xiao Zeng, Mi Zhang, Hongyi Wang, Xiaoyang Wang, Praneeth Vepakomma, Abhishek Singh, Hang Qiu, Xinghua Zhu, Jianzong Wang, Li Shen, Peilin Zhao, Yan Kang, Yang Liu, Ramesh Raskar, Qiang Yang, Murali Annavaram, Salman Avestimehr

ICCD 2018

Minimizing Thermal Variation in Heterogeneous HPC Systems with FPGA Nodes

Yingyi Luo, Xiaoyang Wang, Seda Ogrenci-Memik, Gokhan Memik, Kazutomo Yoshii, Pete Beckman

HPDC 2018

Hard Real-time Scheduling for Parallel Run-time Systems

Peter Dinda, Xiaoyang Wang, Jinghang Wang, Chris Beauchene, Conor Hetland