Publications (Google Scholar)

Conference and Journal

• BeMap: Balanced Message Passing for Fair Graph Neural Network.
  Xiao Lin, Jian Kang, Weilin Cong, Hanghang Tong
  Learning on Graphs Conference 2023 (LOG23)
  

• Do We Really Need Complicated Model Architectures For Temporal Networks? (Oral) [Talk]
  Weilin Cong, Si Zhang, Jian Kang, Baichuan Yuan, Hao Wu, Xin Zhou, Hanghang Tong, Mehrdad Mahdavi
  International Conference on Learning Representations 2023 (ICLR23)
  

• Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection. [Talk]
  Weilin Cong, Mehrdad Mahdavi
  Artificial Intelligence and Statistics 2023 (AISTATS23)
  

• DyFormer : A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability.
  Weilin Cong, Yanhong Wu, Yuandong Tian, Mengting Gu, Yinglong Xia, Jason Chen, Mehrdad Mahdavi
  SIAM International Conference on Data Mining (SDM23)
  

• Predicting protein–ligand docking structure with graph neural network.
  Huaipan Jiang, Jian Wang, Weilin Cong, Yihe Huang, Morteza Ramezani, Anup Sarma, Nikolay V Dokholyan, Mehrdad Mahdavi, Mahmut Kandemir
  Journal of Chemical Information and Modeling.
  

• Understanding the structural components behind the psychological effects of autonomous sensory meridian response (ASMR) with machine learning and experimental methods.
  Ryan Tan, Heather Shoenberger, Weilin Cong, Mehrdad Mahdavi
  Journal of Media Psychology: Theories, Methods, and Applications.
  

• Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks. [Slides] [Poster]
  Morteza Ramezani*, Weilin Cong*, Mehrdad Mahdavi, Mahmut Kandemir, Anand Sivasubramaniam. (* equal contributions)
  International Conference on Learning Representations (ICLR 2022).
  

• On Provable Benefits of Depth in Training Graph Convolutional Networks . [Slides] [Poster] [Talk (中文)]
  Weilin Cong, Morteza Ramezani, Mehrdad Mahdavi.
  Advances in Neural Information Processing Systems (NeurIPS 2021).
  

• GCN meets GPU: Decoupling "When to Sample" from "How to Sample" .
  Morteza Ramezani*, Weilin Cong*, Mehrdad Mahdavi, Anand Sivasubramaniam, Mahmut Kandemir. (* equal contributions)
  Advances in Neural Information Processing Systems (NeurIPS 2020).
  

• Encrypted rich-data steganography using generative adversarial networks.
  Dule shu, Weilin Cong, Jiaming Chai, and Conrad Tucker.
  Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning (WiseML 2020).
  

• Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networks.
  Weilin Cong, Rana Forsati, Mahmut Kandemir, and Mehrdad Mahdavi.
  Knowledge Discovery and Data mining (KDD 2020).
  

• End-to-End Cascade CNN for Simultaneously Face Detection and Alignment.
  Sanyuan Zhao, Hongmei Song, Weilin Cong, Qi Qi, and Hui Tian.
  International Conference on Virtual Reality and Visualization (ICVRV 2017).
  

Preprint

• GraphEditor: An Efficient Graph Representation Learning and Unlearning Approach.
  Weilin Cong, Mehrdad Mahdavi
  

• On the Importance of Sampling in Learning Graph Convolutional Networks.
  Weilin Cong, Morteza Ramezani, Mehrdad Mahdavi