10 papers
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…
When Brain Networks Travel: Learning Beyond Site
Yingxu Wang, Kunyu Zhang, Yanwu Yang +4
Graph-based learning on functional magnetic resonance imaging (fMRI) has shown strong potential for brain network analysis. However, existing methods degrade under cross-site out-o…
DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation
Yingxu Wang, Xinwang Liu, Mengzhu Wang +2
Graph Domain Adaptation (GDA) aims to transfer graph classifiers across domains with both semantic and topological shifts. Existing Euclidean adversarial methods face two challenge…
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…
DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation
Yingxu Wang, Kunyu Zhang, Jiaxin Huang +4
Graph domain adaptation (GDA) aims to transfer knowledge from a labeled source graph to an unlabeled target graph under distribution shifts. However, existing methods are largely f…