Heng Changchangh17 at tsinghua dot org dot cn I received my Ph.D. degree from 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, explainability, and reliability on graph/relational structured data. I am also broadly interested in trustworthy generative AI and knowledge-augmented LLMs. Email / GitHub / Google Scholar / LinkedIn |
|
Professional Services |
|
Toolkits |
Publications |
[21]AutoGL: A Library for Automated Graph LearningZiwei Zhang, Yijian Qin, Zeyang Zhang, Chaoyu Guan, Jie Cai, Heng Chang, Jiyan Jiang, Haoyang Li, Zixin Sun, Beini Xie, Yang Yao, Yipeng Zhang, Xin Wang, Wenwu Zhu Under Review, 2024 preprint / |
[20]Path-based Explanation for Knowledge Graph CompletionHeng Chang*, Jiangnan Ye*, Alejo Lopez Avila, Jinhua Du, Jia Li Under Review, 2024 * Equal contribution preprint / |
[19]Hierarchical Graph Latent Diffusion Model for Molecule GenerationTian Bian, Yifan Niu, Heng Chang, Divin Yan, Tingyang Xu, Yu Rong, Jia Li, Hong Cheng Under Review, 2024 preprint / |
[18]Lightweight Graph Neural Network Search with Graph SparsificationBeini Xie, Heng Chang, Ziwei Zhang, Zeyang Zhang, Simin Wu, Xin Wang, Yuan Meng, Wenwu Zhu Under Review, 2024 preprint / |
[17]QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language ModelsYuhui Xu, Lingxi Xie, Xiaotao Gu, Xin Chen, Heng Chang, Hengheng Zhang, Zhensu Chen, Xiaopeng Zhang, Qi Tian In proceedings of 12th International Conference on Learning Representations (ICLR), 2024 paper / code / huggingface / |
[16]Revisiting Adversarial Attacks on Graph Neural Networks for Graph ClassificationXin Wang, Heng Chang, Beini Xie, Tian Bian, Shiji Zhou, Daixin Wang, Zhiqiang Zhang, Wenwu Zhu IEEE Transactions on Knowledge and Data Engineering (TKDE), 2023 paper / |
[15]TM2D: Bimodality Driven 3D Dance Generation via Music-Text IntegrationKehong Gong*, Dongze Lian*, Heng Chang, Chuan Guo, Xinxin Zuo, Zhihang Jiang, Xinchao Wang In proceedings of IEEE / CVF International Conference on Computer Vision (ICCV), 2023 * Equal contribution paper / code / webpage / |
[14]Adversarially Robust Neural Architecture Search for Graph Neural NetworksBeini Xie*, Heng Chang*, Ziwei Zhang, Xin Wang, Daixin Wang, Zhiqiang Zhang, Rex Ying, Wenwu Zhu In proceedings of IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023 * Equal contribution paper / |
[13]Improving Generalization of Meta Learning with Inverted Regularization at Inner-levelLianzhe Wang, Shiji Zhou, Shanghang Zhang, Xu Chu, Heng Chang, Wenwu Zhu In proceedings of IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023 paper / |
[12]Knowledge Graph Completion with Counterfactual AugmentationHeng Chang, Jie Cai, Jia Li In proceedings of The 2023 ACM Web Conference (TheWebConf (WWW)), 2023 paper / webpage / |
[11]Semi-Supervised Hierarchical Graph ClassificationJia Li, Yongfeng Huang, Heng Chang, Yu Rong IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 paper / code / |
[10]Rethinking Embedded Unsupervised Feature Selection: A Simple Joint ApproachHeng Chang, Jun Guo, Wenwu Zhu IEEE Transactions on Big Data (TBD), 2022 paper / code / |
[9]Adversarial Attack Framework on Graph Embedding Models with Limited KnowledgeHeng 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 / |
[8]Online Continual Adaptation with Active Self-TrainingShiji 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 / |
[7]Not All Low-Pass Filters are Robust in Graph Convolutional NetworksHeng Chang, Yu Rong, Tingyang Xu, Yatao Bian, Shiji Zhou, Xin Wang, Junzhou Huang, Wenwu Zhu In proceedings of 35th Conference on Neural Information Processing Systems (NeurIPS), 2021 paper / code / |
[6]Spectral Graph Attention Network with Fast Eigen-approximationHeng 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 |
[5]AutoGL: A Library for Automated Graph LearningChaoyu 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 / |
[4]Power up! Robust Graph Convolutional Network via Graph PoweringMing Jin*, Heng Chang*, Wenwu Zhu, Somayeh Sojoudi In proceedings of 35th AAAI Conference on Artificial Intelligence (AAAI), 2021 * Equal contribution paper / |
[3]Implicit Graph Neural NetworksFangda Gu*, Heng Chang*, Wenwu Zhu, Somayeh Sojoudi, Laurent El Ghaoui In proceedings of 34th Conference on Neural Information Processing Systems (NeurIPS), 2020 * Equal contribution paper / code / |
[2]A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding ModelsHeng 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 / |
[1]Preserving Ordinal Consensus: Towards Feature Selection for Unlabeled DataJun Guo, Heng Chang, Wenwu Zhu In proceedings of 34th AAAI Conference on Artificial Intelligence (AAAI), 2020 paper / code / |
MiscellaneousMy name in Chinese is 常恒. 🏀⚾🎧🍼🐆🐾 |
|
Design and source code from Jon Barron's and Leonid Keselman's websites |