Heng Chang

changh17 at tsinghua dot org dot cn

I am a final year PhD candidate in the Tsinghua-Berkeley Shenzhen Institute, Tsinghua University co-advised by Prof. Wenwu Zhu and Prof. Somayeh Sojoudi. I received my Bachelor's Degrees in the Department of Electronic Engineering and the School of Economics and Management from Tsinghua University in 2017. In the past, I was also fortunate to work with Prof. Stratos Idreos as an undergraduate research intern at DASLab in Harvard in 2016, with Yu Rong and Prof. Junzhou Huang as a PhD research intern at Tencent AI Lab in 2018, 2020 and 2021, and with Zhiqiang Zhang as a PhD research intern at Ant Group in 2021. I was also a ZhenIntern at ZhenFund in 2022.

My research focuses on representation learning, adversarial robustness and machine learning on graph/relational structured data.

Email  /  GitHub  /  Google Scholar  /  LinkedIn

profile photo

Professional Services

  • Program Committee Member / Reviewer:
    Journals: IEEE TPAMI, IEEE TNNLS, IEEE TKDE, ACM TKDD, TMLR
    Conferences: AAAI (2021(top 25%), 2022, 2023), WWW 2021, AISTATS 2021, ICML (2021, 2022), NeurIPS (2021, 2022), ICLR (2022, 2023), ICME 2022, IJCAI 2022, KDD 2022, LoG 2022

Toolkits

  • AutoGL: A toolkit and platform towards automatic machine learning on graphs.
    code / webpage /

Publications

Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification


Beini Xie*, Heng Chang*, Xin Wang, Tian Bian, Shiji Zhou, Daixin Wang, Zhiqiang Zhang, Wenwu Zhu
Under review, 2022
paper /

* Equal contribution

Semi-Supervised Hierarchical Graph Classification


Jia Li, Yongfeng Huang, Heng Chang, Yu Rong
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
paper /

Rethinking Embedded Unsupervised Feature Selection: A Simple Joint Approach


Heng Chang*, Jun Guo*, Wenwu Zhu
IEEE Transactions on Big Data (TBD), 2022
paper / code /

* Equal contribution

Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge


Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Honglei Zhang, Peng Cui, Xin Wang, Wenwu Zhu, Junzhou Huang
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2022
paper / code /

Online Continual Adaptation with Active Self-Training


Shiji Zhou, Han Zhao, Shanghang Zhang, Lianzhe Wang, Heng Chang, Zhi Wang, Wenwu Zhu
In proceedings of 25th International Conference on Artificial Intelligence and Statistics (AISTATS), 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 and Wenwu Zhu
In proceedings of 35th Conference on Neural Information Processing Systems (NeurIPS), 2021
paper / code /

Spectral Graph Attention Network with Fast Eigen-approximation


Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Somayeh Sojoudi, Junzhou Huang, Wenwu Zhu
In proceedings of 30th ACM International Conference on Information and Knowledge Management (CIKM), 2021
paper / code /

Previous version on DLG-KDD’21

AutoGL: A Library for Automated Graph Learning


Chaoyu Guan, Ziwei Zhang, Haoyang Li, Heng Chang, Zeyang Zhang, Yijian Qin, Jiyan Jiang, Xin Wang, Wenwu Zhu
Geometrical and Topological Representation Learning (GTRL) Workshop at the 9th International Conference on Learning Representations (ICLR), 2021
paper / code /

Power up! Robust Graph Convolutional Network via Graph Powering


Ming Jin*, Heng Chang*, Wenwu Zhu, Somayeh Sojoudi
In proceedings of 35th AAAI Conference on Artificial Intelligence (AAAI), 2021
paper /

* Equal contribution

Implicit Graph Neural Networks


Fangda Gu*, Heng Chang*, Wenwu Zhu, Somayeh Sojoudi, Laurent El Ghaoui
In proceedings of 34th Conference on Neural Information Processing Systems (NeurIPS), 2020
paper / code /

* Equal contribution

A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models


Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Honglei Zhang, Peng Cui, Wenwu Zhu, Junzhou Huang
In proceedings of 34th AAAI Conference on Artificial Intelligence (AAAI), 2020
paper / code /

Preserving Ordinal Consensus: Towards Feature Selection for Unlabeled Data


Jun Guo, Heng Chang, Wenwu Zhu
In proceedings of 34th AAAI Conference on Artificial Intelligence (AAAI), 2020
paper / code /


Miscellaneous

My Chinese name is 常恒.


Design and source code from Jon Barron's and Leonid Keselman's websites