Zengfeng Huang Professor School of Data Science, Fudan University, Shanghai Email: huangzf@fudan.edu.cn

About Me

I am currently a Professor in the School of Data Science, Fudan University. I was a Research Fellow in CSE, UNSW, working with Professor Xuemin Lin, and a Postdoc in MADALGO, Aarhus University, working with Professor Lars Arge. I did my PhD at HKUST in CSE. My supervisor was Ke Yi. I obtained my B.S. degree in Computer Science from Zhejiang University in 2008.

Research Interests

Graph Representation Learning; Differential Privacy; Bandits and Online Learning; Distributed and Streaming Algorithms; Communication Complexity and Lower Bounds.

Selected Awards

• ICML 2018 Best Paper Runner Up Award.
• PODS 2022 Alberto. O. Mendelzon Test-of-Time Award.
• WAIC 2020 Youth Outstanding Paper Award Honorable Mention.
• WAIC 2023 Youth Outstanding Paper Award Honorable Mention.

Openings (Drop me an email if you are interested)

• I am looking for self-motivated students. Candidates with strong background in math or programming are especially welcome.


• Postdoc positions are also available.

Conference Publications

• The Communication Complexity of Distributed Maximization
  Xiaoyi Zhu, Yuxiang Tian, Zengfeng Huang
  COCOON 2024 

• Distributed Thresholded Counting with Limited Interaction
  Xiaoyi Zhu, Yuxiang Tian, Zengfeng Huang
  KDD 2024 

• Enhancing Performance of Coarsened Graphs with Gradient-matching
  Wenjie Yang, Shengzhong Zhang, Zengfeng Huang
  ICASSP 2024 

• Space Complexity of Euclidean Clustering
  Xiaoyi Zhu, Yuxiang Tian, Lingxiao Huang, Zengfeng Huang
  SoCG 2024 

• StructComp: Substituting propagation with Structural Compression in Training Graph Contrastive Learning
  Shengzhong Zhang, Wenjie Yang, Xinyuan Cao, Hongwei Zhang, Zengfeng Huang
  ICLR 2024 

• Optimal Matrix Sketching over Sliding Windows
  Hanyan Yin, Dongxie Wen, Jiajun Li, Zhewei Wei, Xiao Zhang, Zengfeng Huang, Feifei Li
  VLDB 2024 

• FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
  Kezhao Huang, Haitian Jiang, Minjie Wang, Guangxuan Xiao, David Wipf, Xiang Song, Quan Gan, Zengfeng Huang, Jidong Zhai, Zheng Zhang
  VLDB 2024 

• Adversarially Robust Distributed Count Tracking via Partial Differential Privacy
  Zhongzheng Xiong, Xiaoyi Zhu, Zengfeng Huang
  NeurIPS 2023 

• Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
  Liang Yan, Gengchen Wei, Chen Yang, Shengzhong Zhang, Zengfeng Huang
  NeurIPS 2023 

• On Coresets for Clustering in Small Dimensional Euclidean Spaces
  Lingxiao Huang, Ruiyuan Huang, Zengfeng Huang, Xuan Wu
  ICML 2023 

• Efficient Tree-SVD for Subset Node Embedding over Large Dynamic Graphs
  Xinyu Du, Xingyi Zhang, Sibo Wang, Zengfeng Huang
  SIGMOD 2023 

• Transformers from an Optimization Perspective
  Yongyi Yang, Zengfeng Huang, David Wipf.
  NeurIPS 2022 

• Lipschitz Bandits with Batched Feedback
  Yasong Feng, Zengfeng Huang, Tianyu Wang.
  NeurIPS 2022 

• Optimal Clustering with Noisy Queries via Multi-Armed Bandit
  Jinghui Xia, Zengfeng Huang.
  ICML 2022 

• BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction
  Bisheng Li, Min Zhou, Shengzhong Zhang, Menglin Yang, Defu Lian, Zengfeng Huang.
  SIGIR 2022 (short) 

• Compressive Sensing Approaches for Sparse Distribution Estimation Under Local Privacy
  Zhongzheng Xiong, Jialin Sun, Xiaojun Mao, Jian Wang, Ying Shan, Zengfeng Huang.
  The Web Conference (WWW 2022) 

• Why Propagate Alone? Parallel Use of Labels and Features on Graphs
  Yangkun Wang, Jiarui Jin, Weinan Zhang, Yongyi Yang, Jiuhai Chen, Quan Gan, Yong Yu, Zheng Zhang, Zengfeng Huang, David Wipf.
  ICLR 2022 

• Understanding Bandits with Graph Feedback
  Houshuang Chen, Zengfeng Huang, Shuai Li, Chihao Zhang.
  NeurIPS 2021 

• BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
  Mingguo He, Zhewei Wei, Zengfeng Huang, Hongteng Xu.
  NeurIPS 2021 

• Graph Neural Networks Inspired by Classical Iterative Algorithms
  (Selected for long talk 3% acceptance rate)
  Yongyi Yang, Tang Liu, Yangkun Wang, Jinjing Zhou, Quan Gan, Zhewei Wei, Zheng Zhang, Zengfeng Huang, David Wipf.
  ICML 2021 

• Scaling Up Graph Neural Networks Via Graph Coarsening.
  Zengfeng Huang, Shenzhong Zhang, Chong Xi, Tang Liu, Min Zhou.
  KDD 2021 

• Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning.
  Menglin Yang, Min Zhou, Marcus Kalander, Zengfeng Huang, Irwin King.
  KDD 2021 

• Learning Based Proximity Matrix Factorization for Node Embedding.
  Xingyi Zhang, Kun Xie, Sibo Wang, Zengfeng Huang.
  KDD 2021 

• PathQG: Neural Question Generation from Facts
  Siyuan Wang, Zhongyu Wei, Zhihao Fan, Zengfeng Huang, Weijian Sun, Qi Zhang, Xuanjing Huang.
  EMNLP 2020  

• Automatic Term Name Generation for Gene Ontology: Task and Dataset
  Yanjian Zhang, Qin Chen, Yiteng Zhang, Zhongyu Wei, Yixu Gao, Jiajie Peng, Zengfeng Huang, Weijian Sun, Xuanjing Huang.
  EMNLP 2020 (Findings) 

• Simple and Deep Graph Convolutional Networks
  Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, Yaliang Li.
  ICML 2020 

• SCE: Scalable Network Embedding from Sparsest Cut.
  Shengzhong Zhang, Zengfeng Huang, Haicang Zhou, Ziang Zhou
  KDD 2020 

• Personalized PageRank to a Target Node, Revisited.
  Hanzhi Wang, Zhewei Wei, Junhao Gan, Sibo Wang, Zengfeng Huang
  KDD 2020 

• Joint Representation Learning of Legislator and Legislation for Roll Call Prediction
  Yuqiao Yang#, Xiaoqiang Lin#, Geng Lin, Zengfeng Huang, Changjian Jiang and Zhongyu Wei
  IJCAI 2020 

• Optimal Sparsity-Sensitive Bounds for Distributed Mean Estimation
  Zengfeng Huang, Ziyue Huang, Yilei Wang, and Ke Yi
  Conference on Neural Information Processing Systems (NeurIPS 19) 

• Understanding Graph Neural Networks via Trajectory Analysis
  Ziqiao Meng, Jin Dong, Zengfeng Huang, Irwin King
  NeurIPS 2019 Graph Representation Learning Workshop 

• GB-KMV: An Augmented KMV Sketch for Approximate Containment Similarity Search
  Yang Yang, Ying Zhang, Wenjie Zhang, Zengfeng Huang
  IEEE International Conference on Data Engineering (ICDE 19) 

• Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices (Best Paper Runner Up Award)
  Zengfeng Huang
  International Conference on Machine Learning (ICML 18), Stockholm. (The full version with improved results and presentation appears in JMLR 2019)  

• Efficient Matrix Sketching over Distributed Data
  Zengfeng Huang, Xuemin Lin, Wenjie Zhang, and Ying Zhang
  Proc. ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems (PODS 17) 

• Tracking Matrix Approximation over Distributed Sliding Windows
  Haida Zhang, Zengfeng Huang, Zhewei Wei, Wenjie Zhang, and Xuemin Lin
  IEEE International Conference on Data Engineering (ICDE 17) 

• SKYPE: Top-k Spatial-keyword Publish/Subscribe Over Sliding Window
  Xiang Wang, Ying Zhang, Wenjie Zhang, Xuemin Lin, Zengfeng Huang
  International Conference on Very Large Data Bases (VLDB 2016) 

• Clairvoyant Mechanism for Online Auctions
  Philipp Brandes, Zengfeng Huang, Hsin-Hao Su, and Roger Wattenhofer
  To appear in COCOON 2016 

• Dynamic graph stream algorithms in o(n) space
  Zengfeng Huang and Pan Peng
  International Colloquium on Automata, Languages, and Programming (ICALP 2016), Rome, Italy. 

• Communication Complexity of Approximate Maximum Matching in Distributed Graph Data
  Zengfeng Huang, Bozidar Radunovic, Milan Vojnovic and Qin Zhang
  Proc. Symposium on Theoretical Aspects of Computer Science (STACS 15), Munich, Germany, March 2015. 

• The Communication Complexity of Distributed epsilon-Approximations
  Zengfeng Huang and Ke Yi
  IEEE Symposium on Foundations of Computer Science (FOCS 2014). 

• Mergeable Summaries
  Pankaj K. Agarwal, Graham Cormode, Zengfeng Huang, Jeff M. Phillips, Zhewei Wei, and Ke Yi
  Proc. ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems (PODS 12). Scottsdale, Arizona, U.S.A., May 2012. 

• Randomized Algorithms for Tracking Distributed Count, Frequencies, and Ranks [slides] 
  Zengfeng Huang, Ke Yi, and Qin Zhang
  Proc. ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems (PODS 12). Scottsdale, Arizona, U.S.A., May 2012. 

• Sampling Based Algorithms for Quantile Computation in Sensor Networks [slides] 
  Zengfeng Huang, Lu Wang, Ke Yi, and Yunhao Liu 
  ACM SIGMOD International Conference on Management of Data (SIGMOD), June 2011.
  
  
• Optimal Sampling Algorithms for Frequency Estimation in Distributed Data [slides]
  Zengfeng Huang, Ke Yi, Yunhao Liu, and Guihai Chen
  IEEE INFOCOM, April 2011.
  

Journal Publications

• Lipschitz Bandits with Batched Feedback
  Yasong Feng, Zengfeng Huang, Tianyu Wang
  IEEE Transactions on Information Theory 2023. 

• Exploiting Neighbor Effect: Conv-Agnostic GNN Framework for Graphs With Heterophily
  Jie Chen, Shouzhen Chen, Junbin Gao, Zengfeng Huang, Junping Zhang, Jian Pu
  IEEE Transactions on Neural Networks and Learning Systems 2023. 

• Effective stabilized self-training on few-labeled graph data
  Ziang Zhou, Jieming Shi, Shengzhong Zhang, Zengfeng Huang, Qing Li
  Information Sciences 2023. 

• Learning Regularized Noise Contrastive Estimation for Robust Network Embedding
  Hao Xiong, Junchi Yan, Zengfeng Huang
  IEEE Transactions on Knowledge and Data Engineering. (TKDE 2022) 

• Communication-Efficient Distributed Covariance Sketch, with Application to Distributed PCA
  Zengfeng Huang, Xuemin Lin, Wenjie Zhang, Ying Zhang
  Journal of Machine Learning Research. (JMLR 2021) 

• Efficient and High-Quality Seeded Graph Matching: Employing Higher-order Structural Information
  Haida Zhang, Zengfeng Huang, Xuemin Lin, Zhe Lin, Wenjie Zhang, Ying Zhang
  Transactions on Knowledge Discovery from Data. (TKDD 2021) 

• Communication complexity of approximate maximum matching in the message-passing model
  Zengfeng Huang, Bozidar Radunovic, Milan Vojnovic, Qin Zhang
  Distributed Computing 2020 

• Ghost imaging based on Y-net: a dynamic coding and decoding approach
  Ruiguo Zhu, Hong Yu, Zhijie Tan, Ronghua Lu, ShenSheng Han, Zengfeng Huang, Jian Wang
  Optics Express 2020 

• Some mathematical problems in ghost imaging
  Jian Wang, Zhishen Tong, Chenyu Hu, Mengchu Xu, Zengfeng Huang
  Acta Optica Sinica 2020 

• Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices
  Zengfeng Huang
  Journal of Machine Learning Research. (JMLR 2019) 

• Randomized Algorithms for Tracking Distributed Count, Frequencies, and Ranks  
  Zengfeng Huang, Ke Yi, and Qin Zhang
  Algorithmica 2019. 

• Dynamic graph stream algorithms in o(n) space
  Zengfeng Huang and Pan Peng
  Algorithmica 2019 

• Optimization of light fields in ghost imaging using dictionary learning
  Chenyu Hu, Zhishen Tong, Zhentao Liu, Zengfeng Huang, Jian Wang, and Shensheng Han
  Optics Express 2019. 

• The Communication Complexity of Distributed epsilon-Approximations
  Zengfeng Huang and Ke Yi
  SIAM Journal on Computing (SICOMP 2017). 

• Top-k spatial-keyword publish/subscribe over sliding window
  Xiang Wang, Ying Zhang, Wenjie Zhang, Xuemin Lin, Zengfeng Huang
  The VLDB Journal 2016 

• Mergeable Summaries
  Pankaj K. Agarwal, Graham Cormode, Zengfeng Huang, Jeff M. Phillips, Zhewei Wei, and Ke Yi
  ACM Transactions on Database Systems (TODS 2013) 

---