Shiji Zhou

zhoushiji00@gmail.com

I am a Postdoc researcher at Department of Automation, Tsinghua University, advised by Prof. Qionghai Dai. I obtained my Ph.D. degree in Computer Science at Tsinghua University, advised by Prof. Wenwu Zhu and Prof. Zhi Wang. I received my Bachelor's Degrees in Chinese Academy of Science - Beihang University, Hua Luogeng Mathematics Honors Class in 2017.

My research interest lies in optimization algorithms for deep learning when dealing with changing environments and multi-objectives. To this end, my research mainly focuses on online and stochastic optimization, especially in dynamic and multi-objective scenarios.

PontTuset
Publications
Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification
Xin Wang, Heng Chang, Beini Xie, Tian Bian, Shiji Zhou, Daixin Wang, Zhiqiang Zhang, Wenwu Zhu
TKDE 2023 [paper]
Model-free Reinforcement Learning with Stochastic Reward Stabilization for Recommender Systems
Tianchi Cai*, Shenliao Bao*, Jiyan Jiang*, Shiji Zhou, Wenpeng Zhang, Lihong Gu, Jinjie Gu, Guannan Zhang
SIGIR 2023 [paper]
Collaborative Edge Caching: a Meta Reinforcement Learning Approach with Edge Sampling
Yinan Mao*, Bowei He*, Shiji Zhou, Chen Ma, Zhi Wang
ICME 2023 [paper]
Dynamic Edge Caching via Online Meta-RL
Yinan Mao*, Shiji Zhou*, Haochen Liu, Zhi Wang, Wenwu Zhu
IJCNN 2023 [paper]
Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning
Tianchi Cai, Wenpeng Zhang, Shiji Zhou, Jiyan Jiang, Xierui Song, Li Yu, Lihong Gu, Xiaodong Zeng, Jinjie Gu, Guannan Zhang
WSDM 2023 Best Paper Honorable Mention Award [paper]
Improving Generalization of Meta-Learning With Inverted Regularization at Inner-Level
Lianzhe Wang*, Shiji Zhou*, Shanghang Zhang, Xu Chu, Heng Chang, Wenwu Zhu
CVPR 2023 [paper]
Multi-Objective Online Learning
Jiyan Jiang*, Wenpeng Zhang*, Shiji Zhou, Lihong Gu, Xiaodong Zeng, Wenwu Zhu
ICLR 2023 Spotlight [paper]
On the Convergence of Stochastic Multi-Objective Gradient Manipulation and Beyond
Shiji Zhou*, Wenpeng Zhang*, Jiyan Jiang, Wenliang Zhong, Jinjie Gu, Wenwu Zhu
NeurIPS 2022[paper]
Algorithms and theory for supervised gradual domain adaptation
Jing Dong, Shiji Zhou, Baoxiang Wang, Han Zhao
TMLR 2022[paper]
Online continual adaptation with active self-training
Shiji Zhou, Han Zhao, Shanghang Zhang, Lianzhe Wang, Heng Chang, Zhi Wang, Wenwu Zhu
AISTATS 2022[paper]
Active gradual domain adaptation: dataset and approach
Shiji Zhou, Lianzhe Wang, Shanghang Zhang, Zhi Wang, Wenwu Zhu
IEEE Transactions on Multimedia 2022[paper]
Not all low-pass filters are robust in graph convolutional networks
Heng Chang, Yu Rong, Tingyang Xu, Yatao Bian, Shiji Zhou, Xin Wang, Junzhou Huang, Wenwu Zhu
NeurIPS 2021[paper]
Caching in dynamic environments: A near-optimal online learning approach
Shiji Zhou, Zhi Wang, Chenghao Hu, Yinan Mao, Haopeng Yan, Chuan Wu, Shanghang Zhang, Wenwu Zhu
IEEE Transactions on Multimedia 2021[paper]