GTAT: empowering graph neural networks with cross attention
Top Cited Papers
Open Access
- 8 February 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-13
Abstract
Graph Neural Networks (GNNs) serve as a powerful framework for representation learning on graph-structured data, capturing the information of nodes by recursively aggregating and transforming the neighboring nodes’ representations. Topology in graph plays an important role in learning graph representations and impacts the performance of GNNs. However, current methods fail to adequately integrate topological information into graph representation learning. To better leverage topological information and enhance representation capabilities, we propose the Graph Topology Attention Networks (GTAT). Specifically, GTAT first extracts topology features from the graph’s structure and encodes them into topology representations. Then, the representations of node and topology are fed into cross attention GNN layers for interaction. This integration allows the model to dynamically adjust the influence of node features and topological information, thus improving the expressiveness of nodes. Experimental results on various graph benchmark datasets demonstrate GTAT outperforms recent state-of-the-art methods. Further analysis reveals GTAT’s capability to mitigate the over-smoothing issue, and its increased robustness against noisy data.Keywords
This publication has 27 references indexed in Scilit:
- ALIEN: Attention-guided cross-resolution collaborative network for 3D gastric cancer segmentation in CT imagesBiomedical Signal Processing and Control, 2024
- MutualFormer: Multi-modal Representation Learning via Cross-Diffusion AttentionInternational Journal of Computer Vision, 2024
- Nano scale instance-based learning using non-specific hybridization of DNA sequencesCommunications Engineering, 2023
- Limit and screen sequences with high degree of secondary structures in DNA storage by deep learning methodComputers in Biology and Medicine, 2023
- MolScribe: Robust Molecular Structure Recognition with Image-to-Graph GenerationJournal of Chemical Information and Modeling, 2023
- Spatial graph convolutional neural network via structured subdomain adaptation and domain adversarial learning for bearing fault diagnosisNeurocomputing, 2022
- Representation learning of graphs using graph convolutional multilayer networks based on motifsNeurocomputing, 2021
- Topological data analysis: Concepts, computation, and applications in chemical engineeringComputers & Chemical Engineering, 2021
- Hypergraph convolution and hypergraph attentionPattern Recognition, 2021
- Early Stopping - But When?1998