Can Modifying Data Address Graph Domain Adaptation?

R Huang, J Xu, X Jiang, R An, Y Yang - Proceedings of the 30th ACM …, 2024 - dl.acm.org
Graph neural networks (GNNs) have demonstrated remarkable success in numerous graph
analytical tasks. Yet, their effectiveness is often compromised in real-world scenarios due to …

Extracting Training Data from Molecular Pre-trained Models

R Huang, J Xu, Z Yang, X Si, X Jiang… - Advances in …, 2025 - proceedings.neurips.cc
Abstract Graph Neural Networks (GNNs) have significantly advanced the field of drug
discovery, enhancing the speed and efficiency of molecular identification. However, training …

BrainODE: Dynamic Brain Signal Analysis via Graph-Aided Neural Ordinary Differential Equations

K Han, Y Yang, Z Huang, X Kan, Y Yang, Y Guo… - arxiv preprint arxiv …, 2024 - arxiv.org
Brain network analysis is vital for understanding the neural interactions regarding brain
structures and functions, and identifying potential biomarkers for clinical phenotypes …

[PDF][PDF] Enhancing Cross-domain Link Prediction via Evolution Process Modeling

X Huang, W Chow, Y Zhu, Y Wang, Z Chai… - THE WEB …, 2025 - yangy.org
Dynamic graphs are widespread in the real world [5, 47], their nodes representing entities
and dynamic edges denoting complex interactions between them [20]. For example, in …

A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective

Z Zhao, Y Su, Y Li, Y Zou, R Li, R Zhang - arxiv preprint arxiv:2403.16137, 2024 - arxiv.org
Graph self-supervised learning (SSL) is now a go-to method for pre-training graph
foundation models (GFMs). There is a wide variety of knowledge patterns embedded in the …