Liang Wang
Hi! I am Liang Wang, a PhD candidate at Institute of Automation, Chinese Academy of Sciences (CASIA). I am a member of CRIPAC and advised by Liang Wang, Shu Wu, and Qiang Liu. Previously, I received a B.E. in Software Engineering from Tongji University.
Github / Google Scholar / Email / CV
Research Interests
Education
PhD (selected for the PhD honors program)
at Institute of Automation, Chinese Academy of Sciences
2021 - 2026 (Expected)
Major: Pattern Recognition and Intelligent Systems
Bachelor
at Tongji University
2017 - 2021
Major: Software Engineering
Selected Publications
Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction
Liang Wang, Qiang Liu, Shaozhen Liu, Xin Sun, Shu Wu, Liang Wang
NeurIPS 2024 Rethinking Graph Masked Autoencoders through Alignment and Uniformity
Liang Wang*, Xiang Tao*, Qiang Liu, Shu Wu, Liang Wang
AAAI 2024 Paper Code Poster DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization
Xin Sun, Liang Wang, Qiang Liu, Shu Wu, Zilei Wang, Liang Wang
KDD 2024 Paper Enhancing Temporal Knowledge Graph Forecasting with Large Language Models via Chain-of-History Reasoning
Yuwei Xia, Ding Wang, Qiang Liu, Liang Wang, Shu Wu, Xiaoyu Zhang
ACL 2024 Findings Paper Bi-Level Graph Structure Learning for Next POI Recommendation
Liang Wang, Shu Wu, Qiang Liu, Yanqiao Zhu, Xiang Tao, Mengdi Zhang, Liang Wang
IEEE Transactions on Knowledge and Data Engineering Paper Semantic Evolvement Enhanced Graph Autoencoder for Rumor Detection
Xiang Tao, Liang Wang, Qiang Liu, Shu Wu, Liang Wang
WWW 2024 Paper GSLB: The Graph Structure Learning Benchmark
Zhixun Li, Liang Wang, Xin Sun, Yifan Luo, Yanqiao Zhu, Dingshuo Chen, Yingtao Luo, Xiangxin Zhou, Qiang Liu, Shu Wu, Liang Wang, Jeffrey Xu Yu
NeurIPS 2023 Paper Code
Projects
PyGCL
An easy-to-use library for graph contrastive learning with PyTorch. It implements a wide variety of contrastive objectives, data augmentations, contrasting modes and other utilities useful for implementing and evaluating contrastive learning on graphs.
GSLB
An open-source library built for easy implementation and evaluation of graph structure learning model family. It offers a versatile control of graph dataset laoding, structure learners, structure processors, and a bunch of reproduced models.