Gang Liu / 刘罡

About Me

Hello! My name is Gang Liu. I am a third-year Ph.D. student in Computer Science and Engineering at the University of Notre Dame, advised by Dr. Meng Jiang. I am glad to be a member of the Data Mining towards Decision Making (DM2) Lab, which is directed by Dr. Meng Jiang.

I received my Bachelor degree in Software Engineering at Southwest University, China, in 2021. When I was an undergraduate, I was luckily advised by Prof. Yong Deng and Prof. Fuyuan Xiao.

For my education and research experience, please refer to my Experience.

Research Interest

Graph Machine Learning for Scientific Discovery: The scientific data like molecular graphs is limited in supervision and has imbalanced distribution. I aim to develop data-centric methods that are practically useful for improving the quality of training data through data augmentation [KDD'22/23, NeurIPS'23], pseudo-labeling [KDD'23], and knowledge transfer [NeurIPS'23], and for prediction’s generalization [KDD'22/23, NeurIPS'23] and interpretability [KDD'22, NeurIPS'23].

I’m always eager to collaborate for real scientific impacts. If my work aligns with your project or could aid in new scientific discoveries, please don’t hesitate to reach out for a discussion.

What’s New

Oct 2023 I am excited to receive the NeurIPS 23 travel award. See you in New Orleans!
Sep 2023 One paper “Data-Centric Learning from Unlabeled Graphs with Diffusion Model” accepted by NeurIPS’23.
May 2023 One paper “Semi-Supervised Graph Imbalanced Regression” accepted by KDD’23.
  I am joining the Amazon as an applied scientist intern this summer. See you in Seattle.
Oct 2022 One paper “Network Immunization Strategy by Eliminating Fringe Nodes: A Percolation Perspective” accepted by IEEE Transactions On SMC: Systems.
June 2022 I am excited to receive the KDD 22 Student Travel Award and Notre Dame Conference Presentation Grant to support my travel to KDD’22!
May 2022 One paper “Graph Rationalization with Environment-based Augmentations” accepted by KDD’22.
  One paper “Learning from Counterfactual Links for Link Prediction” accepted by ICML’22.!

Selected Publication (Google Scholar)

  1. Data-Centric Learning from Unlabeled Graphs with Diffusion Model Data-Centric Learning from Unlabeled Graphs with Diffusion Model [Paper] [Code]
    Gang Liu, Eric Inae, Tong Zhao, Jiaxin Xu, Tengfei Luo, Meng Jiang.
    Conference on Neural Information Processing Systems, 2023
  2. Semi-Supervised Graph Imbalanced Regression Semi-Supervised Graph Imbalanced Regression [Paper] [Code] [Video] [Blog]
    Gang Liu, Tong Zhao, Eric Inae, Tengfei Luo, and Meng Jiang.
    ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2023
  3. Graph Rationalization with Environment-based Augmentations Graph Rationalization with Environment-based Augmentations [Paper] [Code]
    Gang Liu, Tong Zhao, Jiaxin Xu, Tengfei Luo, and Meng Jiang.
    ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2022
  4. Learning from Counterfactual Links for Link Prediction Learning from Counterfactual Links for Link Prediction [Paper] [Code]
    Tong Zhao, Gang Liu, Daheng Wang, Wenhao Yu, and Meng Jiang.
    International Conference on Machine Learning, 2022

Service

Last updated: 10/26/2023. Templated adapted from Ankit Sultana and Otilia Stretcu. Thanks for their great work!