7 papers · 1 filter
Learning Propagation Geometry from Message-Passing Feedback
Yingxu Wang, Kunyu Zhang, Xinwang Liu +4
Learning local geometry enables graph neural networks (GNNs) to adapt how they compare and integrate neighborhood information. However, estimating geometry from aggregated represen…
Beyond Site Agreement: Re-estimation for Brain Network Generalization
Yingxu Wang, Kunyu Zhang, Yanwu Yang3 +4
Cross-site out-of-distribution (OOD) generalization in resting-state functional magnetic resonance imaging (rs-fMRI) often relies on learning task-discriminative representations fr…
scGTN: Deep Siamese Graph Transformer Network for Single-cell RNA Sequencing Clustering
Jinke Wu, Yifan Wang, Siyu Yi +5
Single-cell RNA sequencing (scRNA-seq) serves a pivotal role in characterizing gene expression at the cellular level, enabling the identification of cell types and advancing the un…
MOLAR: Learning Multimodal Molecular Representations from Noisy Labels
Yingxu Wang, Kunyu Zhang, Nan Yin +2
Motivation: Noisy labels are a common challenge in molecular property prediction because molecular annotations are often obtained from assays, curated databases, or weak annotation…
Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation
Yingxu Wang, Xinwang Liu, Siyang Gao +1
Source-free graph domain adaptation (SF-GDA) aims to adapt source-trained graph models to unlabeled target graphs when source graphs are no longer accessible. A central obstacle is…
Learning beyond Site Bias for OOD Generalization in Brain Networks
Yingxu Wang, Kunyu Zhang, Yanwu Yang +5
Graph-based learning from functional magnetic resonance imaging (fMRI) has shown strong potential for brain network analysis. However, existing methods often degrade under cross-si…
TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering
Yingxu Wang, Jiaxin Huang, Mengzhu Wang +1
Multi-hop Knowledge Graph Question Answering (KGQA) requires coherent reasoning across relational paths, yet existing methods often treat each reasoning step independently and fail…