Graph Triple Attention Network: A Decoupled Perspective
Not on the map. Why?
Abstract (arXiv)
Graph Transformers (GTs) have recently achieved significant success in the graph domain by effectively capturing both long-range dependencies and graph inductive biases. However, these methods face two primary challenges: (1) multi-view chaos, which results from coupling multi-view information (positional, structural, attribute), thereby impeding flexible usage and the interpretability of the propagation process. (2) local-global chaos, which arises from coupling local message passing with global attention, leading to issues of overfitting and over-globalizing. To address these challenges, we propose a high-level decoupled perspective of GTs, breaking them down into three components and two interaction levels: positional attention, structural attention, and attribute attention, alongside local and global interaction. Based on this decoupled perspective, we design a decoupled graph triple attention network named DeGTA, which separately computes multi-view attentions and adaptively integrates multi-view local and global information. This approach offers three key advantages: enhanced interpretability, flexible design, and adaptive integration of local and global information. Through extensive experiments, DeGTA achieves state-of-the-art performance across various datasets and tasks, including node classification and graph classification. Comprehensive ablation studies demonstrate that decoupling is essential for improving performance and enhancing interpretability. Our code is available at: https://github.com/wangxiaotang0906/DeGTA
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 35 of its 54 references that are in the map. First posted on arXiv 14 Aug 2024.
Builds on
35 of 54 references.
References · 35
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
- 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
- 2020Simple and Deep Graph Convolutional Networkscited by 857
- 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
- 2020Benchmarking Graph Neural Networkscited by 672
23 more
- 2020A Generalization of Transformer Networks to Graphscited by 653
- 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 624
- 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
- 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
- 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 540
- 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 471
- 2021Rethinking Graph Transformers with Spectral Attentioncited by 468
- 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
- 2021Do Transformers Really Perform Bad for Graph Representation?cited by 318
- 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 312
- 2020Towards Deeper Graph Neural Networkscited by 296
- 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
- 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 207
- 2023Graph Inductive Biases in Transformers without Message Passingcited by 150
- 2022NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphscited by 137
- 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
- 2018DeepInf: Social Influence Prediction with Deep Learningcited by 128
- 2021Global Self-Attention as a Replacement for Graph Convolutioncited by 113
- 2024Efficient Tuning and Inference for Large Language Models on Textual Graphscited by 54
- 2023GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learningcited by 32
- 2021Learning Conjoint Attentions for Graph Neural Netscited by 26
- 2024Bridging Local Details and Global Context in Text-Attributed Graphscited by 15
- 2024UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Taskscited by 3
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.