Publications

Selected publications in reverse-chronological order
Full publication list on Google Scholar and DBLP
  1. Wanyu Lin, Baochun Li, and Cong Wang. ”Towards Private Learning on Decentralized Graphs with Local Differential Privacy, ” in IEEE Transactions on Information Forensics & Security (TIFS), 2022.

  2. Wanyu Lin, Hao Lan, Hao Wang, and Baochun Li. ”Orphicx: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks, ” in the Proceedings of the 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022), Oral Presentation, New Orleans, Louisiana, June 19-24, 2022 (Best paper finalist 33/8161=0.4%). [code]

  3. Wanyu Lin, and Baochun Li. ”Status-Aware Signed Heterogeneous Network Embedding with Graph Neural Networks, ” in IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2022.

  1. Wanyu Lin, Hao Lan, and Baochun Li. ”Generative Causal Explanations for Graph Neural Networks, ” in the Proceedings of the 38th International Conference on Machine Learning (ICML 2021), Online, July 18-24, 2021. [presentation slides] [code]

  2. Wanyu Lin, and Baochun Li. ”Medley: Predicting Social Trust in Time-Varying Online Social Networks, ” in the Proceedings of IEEE INFOCOM 2021, Virtual Conference, May 10-13, 2021. [presentation slides]

  3. Wanyu Lin, Helei Cui, Baochun Li, and Cong Wang. ”Privacy-Preserving Similarity Search with Efficient Updates in Distributed Key-Value Stores, ” in IEEE Transactions on Parallel and Distributed Systems, vol. 32, no. 5, pp. 1072-1084, May 2021.

  1. Wanyu Lin, Zhaolin Gao, and Baochun Li. ”Guardian: Evaluating Trust in Online Social Networks with Graph Convolutional Networks, ” in the Proceedings of IEEE INFOCOM, Toronto, Canada, July 6-9, 2020. [presentation slides] [code]

  2. Wanyu Lin, Zhaolin Gao, and Baochun Li. ”Shoestring: Graph-Based Semi-Supervised Classification with Severely Limited Labeled Data, ” in the Proceedings of the 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020), Seattle, Washington, June 16-18, 2020. [presentation slides] [code]

  3. Wanyu Lin, Shengxiang Ji, and Baochun Li. ”Adversarial Attacks on Link Prediction Algorithms Based on Graph Neural Networks, ” in the Proceedings of the 15th ACM ASIA Conference on Computer and Communications Security (ACM ASIACCS 2020), Taipei, Taiwan, October 5-9, 2020.