works on

From the 1 of 13 linked papers with an AI index.

collaborators

13 papers

cs.AI2026

DualHNIE: Dual-Channel Hypergraph Learning for Node Importance Estimation in Heterogeneous Knowledge Graphs

Jiawen Chen, Yanyan He, Qi Shao +4

The paper introduces DualHNIE, a dual‑channel hypergraph framework that constructs meta‑path based hyperedges and employs separate structure‑aware and semantic‑aware encoders with…

cs.LG2026

Weisfeiler Lehman Test on Combinatorial Complexes: Generalized Expressive Power of Topological Neural Networks

Jiawen Chen, Qi Shao, Zhiqiang Ge +2

Topological neural networks have emerged as effective tools for modeling higher-order relational structures beyond pairwise graphs, including hypergraphs, simplicial complexes, and…

cs.LG2026

From Uniform to Learned Graph Priors: Diffusion for Structure Discovery

Qi Shao, Hao Guo, Jiawen Chen +2

Neural relational inference (NRI) methods discover interaction graphs from trajectories through variational reasoning on discrete potential edges. However, these methods typically…

cs.LG2026

CoDCL: Counterfactual-Inspired Augmentation Contrastive Learning for Temporal Link Prediction in Social Networks

Hantong Feng, Duxin Chen, Wenwu Yu

Temporal link prediction is crucial for rapidly growing social networks. Existing methods often overlook the underlying causal mechanisms that drive link formation, making it diffi…

cs.LG2026

CausalCompass: Evaluating the Robustness of Time-Series Causal Discovery in Misspecified Scenarios

Huiyang Yi, Xiaojian Shen, Yonggang Wu +3

Causal discovery from time series is a fundamental task in machine learning. However, its widespread adoption is hindered by a reliance on untestable causal assumptions and by the…

cs.LG2026

Predicting Dynamics of Ultra-Large Complex Systems by Inferring Governing Equations

Qi Shao, Duxin Chen, Jiawen Chen +5

Predicting the behavior of ultra-large complex systems, from climate to biological and technological networks, is a central unsolved challenge. Existing approaches face a fundament…