Xiang Lian — accepted AI-conference papers

2026

Similarity-Guided Structural Matching Learning for Graph Dataset Condensation

Yiyang Zhang, Yutong Ye, Yingbo Zhou, Nan Zhang, Xiang Lian, Mingsong Chen

IJCAI 2026

As graph repositories grow in scale and diversity, training Graph Neural Networks (GNNs) becomes computationally demanding. However, existing graph condensation methods often fail to retain the intrinsic structural patterns of the original graphs, which are essential in graph-based learning. Therefo

Cited by 0 Scholar ↗

2023

InitLight: Initial Model Generation for Traffic Signal Control Using Adversarial Inverse Reinforcement Learning

Yutong Ye, Yingbo Zhou, Jiepin Ding, Ting Wang, Mingsong Chen, Xiang Lian

IJCAI 2023poster

Due to repetitive trial-and-error style interactions between agents and a fixed traffic environment during the policy learning, existing Reinforcement Learning (RL)-based Traffic Signal Control (TSC) methods greatly suffer from long RL training time and poor adaptability of RL agents to other comple…

Cited by 9 Source ↗PDF ↗Scholar ↗