2 papers
cs.LG2026
Decoupling and Damping: Structurally-Regularized Gradient Matching for Multimodal Graph Condensation
Lian Shen, Zhendan Chen, Meijia Song +4
In multimodal graph learning, graph structures that integrate information from multiple sources, such as vision and text, can more comprehensively model complex entity relationship…
cs.LG2025
LOHA: Direct Graph Spectral Contrastive Learning Between Low-pass and High-pass Views
Ziyun Zou, Yinghui Jiang, Lian Shen +2
Spectral Graph Neural Networks effectively handle graphs with different homophily levels, with low-pass filter mining feature smoothness and high-pass filter capturing differences.…