activity
20222026
most citedGraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks

27 citations · 27 across the 6 of their papers we have counts for

collaborators

6 papers

physics.soc-ph2026

Control of Harmful Information Spreading on Adaptive Higher-Order Networks via Group Dissolution

Longzhao Liu, Zhihao Han, Xingru Chen +4

Curbing harmful information contagion remains a critical challenge, motivating platform-level interventions such as group dissolution to sever transmission chains. However, in prac…

physics.soc-ph2026

Immunization on Temporal Higher-Order Networks

Zhihao Han, Longzhao Liu, Xin Wang +3

Network immunization is a powerful tool for controlling contagion processes ranging from infectious diseases to misinformation diffusion. While prior works have focused on pairwise…

physics.soc-ph2026

Identifying vulnerable nodes for hypergraph dismantling via higher-order competition dynamics

Yajing Hao, Longzhao Liu, Xin Wang +3

Network dismantling aims to identify a node removal sequence that can rapidly destroy network connectivity, which is an important problem for understanding the structural fragility…

physics.soc-ph2025

A unified framework for identifying influential nodes in hypergraphs

Yajing Hao, Longzhao Liu, Xin Wang +4

Identifying influential nodes plays a pivotal role in understanding, controlling, and optimizing the behavior of complex systems, ranging from social to biological and technologica…

physics.soc-ph2025

Higher-order network adaptivity: co-evolution of higher-order structure and spreading dynamics

Longzhao Liu, Hongwei Zheng, Zhihao Han +2

The co-evolution of structure and dynamics, known as adaptivity, is a fundamental property in various systems and drives diverse emergent behaviors. However, the adaptivity in prev…

cs.LG2022★ 27 cited

GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks

Kenza Amara, Rex Ying, Zitao Zhang +5

As one of the most popular machine learning models today, graph neural networks (GNNs) have attracted intense interest recently, and so does their explainability. Users are increas…