23 papers
OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradation
Yuze Dai, Zhihan Zhang, Yan Zhao +6
Text-attributed graphs (TAGs) are an important graph data form that combine relational structure with rich node text. However, real-world TAGs are often imperfect, with quality iss…
Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework
Xunkai Li, Guohao Fu, Yuming Ai +4
Multimodal-attributed graphs (MAGs), whose nodes carry modalities such as images and text alongside topological structure, now pervade applications including social platforms, e-co…
Towards Modality-imbalanced Federated Graph Learning: A Data Synthesis-based Approach
Zhengyu Wu, Hongchao Qin, Xunkai Li +3
MultiModal Federated Graph Learning (MM-FGL) offers a natural collaborative training paradigm, but its practical deployment is challenged by two granularities of modality imbalance…
SMGFM: Spectral Multimodal Graph Pretraining for Multimodal-Attributed Graphs
Zhengyu Wu, Xu Wang, Hongchao Qin +4
Multimodal-attributed graphs (MAGs) couple graph topology with node semantics from text, images, and other modalities. Traditional graph learning contextualizes node semantics by c…
Multimodal Graph Negative Learning
Zhengyu Wu, Xu Wang, Hongchao Qin +4
Multimodal attributed graphs (MAGs) integrate graph topology with heterogeneous modality attributes, such as text and images, thereby enabling richer modeling of complex relational…
MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA
Yilong Zuo, Xunkai Li, Jing Yuan +3
Long-document multimodal question answering requires a system to locate sparse evidence in long PDFs and integrate clues from text, tables, images, charts, and complex layouts. Exi…