Multi-view Fuzzy Graph Attention Networks for Enhanced Graph Learning
Jinming Xing, Dongwen Luo, Qisen Cheng, Chang Xue, Ruilin Xing
TL;DR
The paper addresses the challenge of capturing multi-view dependencies in fuzzy graph learning. It introduces Multi-view Fuzzy Graph Attention Network (MFGAT) with a Transformation Block to dynamically fuse multi-view node representations, FGAT convolutions for fuzzy spatial modeling, and a learnable global pooling mechanism for robust graph-level representations. Empirical results on PROTEINS, NCI1, and Mutagenicity show that MFGAT achieves state-of-the-art performance, with three views providing the best trade-off between accuracy and complexity. This work bridges fuzzy rough set theory and multi-view graph learning, offering a versatile framework for enhanced graph classification and potential extensions to other graph tasks.
Abstract
Fuzzy Graph Attention Network (FGAT), which combines Fuzzy Rough Sets and Graph Attention Networks, has shown promise in tasks requiring robust graph-based learning. However, existing models struggle to effectively capture dependencies from multiple perspectives, limiting their ability to model complex data. To address this gap, we propose the Multi-view Fuzzy Graph Attention Network (MFGAT), a novel framework that constructs and aggregates multi-view information using a specially designed Transformation Block. This block dynamically transforms data from multiple aspects and aggregates the resulting representations via a weighted sum mechanism, enabling comprehensive multi-view modeling. The aggregated information is fed into FGAT to enhance fuzzy graph convolutions. Additionally, we introduce a simple yet effective learnable global pooling mechanism for improved graph-level understanding. Extensive experiments on graph classification tasks demonstrate that MFGAT outperforms state-of-the-art baselines, underscoring its effectiveness and versatility.