About Me

I received my bachelor’s degree in 2016 and Ph.D. degree in 2021 (advised by Prof. Lifeng Sun) from the Department of Computer Science and Technology at Tsinghua University. My research is mainly focused on federated learning, lifelong/continual learning, and transfer learning during the postgraduate period.

Currently I am a software engineer at DevTech, NVIDIA.

Education

Ph.D. in Computer Science and Technology

Aug. 2016 - June 2021
Tsinghua University

B.E. in Computer Science and Technology

Aug. 2012 - July 2016
Tsinghua University

B.B. (Second Major) in Business Administration and Management

Sept. 2013 - July 2016
Tsinghua University

Experiences

Engineer, Tech SW

July 2021 - Present
DevTech, NVIDIA, Shanghai, China

Research Intern

June 2020 - Sept. 2020
DAMO Academy, Alibaba, Beijing, China

Research Intern

July 2019 - Jan. 2020
Youtu X-Lab, Tencent, Shenzhen, China

Publications

Conference Papers

Continual Local Training for Better Initialization of Federated Models

Xin Yao, Lifeng Sun

2020 IEEE International Conference on Image Processing (ICIP)

Stick: A Harmonious Fusion of Buffer-based and Learning-based Approach for Adaptive Streaming

Tianchi Huang, Chao Zhou, Rui-Xiao Zhang, Xin Yao, Chenglei Wu, Lifeng Sun

2020 IEEE International Conference on Computer Communications (INFOCOM)

Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating

Xin Yao, Tianchi Huang, Rui-Xiao Zhang, Ruiyu Li, Lifeng Sun

2019 NeurIPS Workshop on Federated Learning for Data Privacy and Confidentiality (FL-NeurIPS 2019)

Generalizing Rate Control Strategies for Real-time Video Streaming via Learning from Deep Learning

Tianchi Huang, Rui-Xiao Zhang, Chenglei Wu, Xin Yao, Chao Zhou, Bing Yu, Lifeng Sun

ACM MM Asia 2019

Comyco: A Video Quality-aware Adaptive Bitrate Approach via Imitation Learning

Tianchi Huang, Chao Zhou, Rui-Xiao Zhang, Xin Yao, Chenglei Wu, Lifeng Sun

The 29th ACM International Conference on Multimedia (ACM MM), 2019

Livesmart: A QoS-Guaranteed Cost-Minimum Framework of Viewer Scheduling for Crowdsourced Live Streaming

Rui-Xiao Zhang, Ming Ma, Tianchi Huang, Haitian Pang, Xin Yao, Chenglei Wu, Jiangchuan Liu, Lifeng Sun

The 29th ACM International Conference on Multimedia (ACM MM), 2019

Being more Effective and Interpretable: Bridging the Gap Between Heuristics and AI for ABR Algorithms

Tianchi Huang, Rui-Xiao Zhang, Xin Yao, Chenglei Wu, Lifeng Sun

ACM SIGCOMM 2019 Conference Posters and Demos

Federated Learning with Additional Mechanisms on Clients to Reduce Communication Costs

Xin Yao, Tianchi Huang, Chenglei Wu, Rui-Xiao Zhang, Lifeng Sun

arXiv preprint arXiv: 1908.05891

Towards Faster and Better Federated Learning: A Feature Fusion Approach

Xin Yao, Tianchi Huang, Chenglei Wu, Rui-Xiao Zhang, Lifeng Sun

2019 IEEE International Conference on Image Processing (ICIP) (Oral)

Enhancing the Crowdsourced Live Streaming: A Deep Reinforcement Learning Approach

Rui-Xiao Zhang, Tianchi Huang, Ming Ma, Haitian Pang, Xin Yao, Chenglei Wu, Lifeng Sun

The 29th ACM Workshop on Network and Operating Systems Support for Digital Audio and Video (NOSSDAV), 2019

Tiyuntsong: A Self-Play Reinforcement Learning Approach for ABR Video Streaming

Tianchi Huang, Xin Yao, Chenglei Wu, Rui-Xiao Zhang, Zhengyuan Pang, Lifeng Sun

2019 IEEE International Conference on Multimedia and Expo (ICME)

Two-Stream Federated Learning: Reduce the Communication Costs

Xin Yao, Chaofeng Huang, Lifeng Sun

2018 IEEE International Conference on Visual Communications and Image Processing (VCIP)

Journal Articles

A Practical Learning-based Approach for Viewer Scheduling in the Crowdsourced Live Streaming

Rui-Xiao Zhang, Tianchi Huang, Ming Ma, Haitian Pang, Xin Yao, Chenglei Wu, Lifeng Sun

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2020 (Volume 16, Issue 25)

Quality-aware Neural Adaptive Video Streaming with Lifelong Imitation Learning

Tianchi Huang, Chao Zhou, Xin Yao, Rui-Xiao Zhang, Chenglei Wu, Bing Yu, Lifeng Sun

IEEE Journal on Selected Areas in Communications (JSAC), 2020

Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning

Xin Yao, Tianchi Huang, Chenglei Wu, Rui-Xiao Zhang, Lifeng Sun

Neural Computation 2019 (Volume 31, Issue 11)