3 papers
cs.LG2026
PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning
Zekai Chen, Miao Zhang, Jiayang Xing +4
Multimodal federated graph learning (MM-FGL) aims to collaboratively learn from decentralized graphs with text and images. However, real-world clients may not share a common modali…
cs.LG2025
JTreeformer: Graph-Transformer via Latent-Diffusion Model for Molecular Generation
Ji Shi, Chengxun Xie, Zhonghao Li +2
The discovery of new molecules based on the original chemical molecule distributions is of great importance in medicine. The graph transformer, with its advantages of high performa…
cs.LG2025
SFi-Former: Sparse Flow Induced Attention for Graph Transformer
Zhonghao Li, Ji Shi, Xinming Zhang +2
Graph Transformers (GTs) have demonstrated superior performance compared to traditional message-passing graph neural networks in many studies, especially in processing graph data w…