DeepAI AI Chat
Log In Sign Up

Graph Joint Attention Networks

by   Tiantian He, et al.

Graph attention networks (GATs) have been recognized as powerful tools for learning in graph structured data. However, how to enable the attention mechanisms in GATs to smoothly consider both structural and feature information is still very challenging. In this paper, we propose Graph Joint Attention Networks (JATs) to address the aforementioned challenge. Different from previous attention-based graph neural networks (GNNs), JATs adopt novel joint attention mechanisms which can automatically determine the relative significance between node features and structural coefficients learned from graph topology, when computing the attention scores. Therefore, representations concerning more structural properties can be inferred by JATs. Besides, we theoretically analyze the expressive power of JATs and further propose an improved strategy for the joint attention mechanisms that enables JATs to reach the upper bound of expressive power which every message-passing GNN can ultimately achieve, i.e., 1-WL test. JATs can thereby be seen as most powerful message-passing GNNs. The proposed neural architecture has been extensively tested on widely used benchmarking datasets, and has been compared with state-of-the-art GNNs for various downstream predictive tasks. Experimental results show that JATs achieve state-of-the-art performance on all the testing datasets.


page 1

page 2

page 3

page 4


Identity-aware Graph Neural Networks

Message passing Graph Neural Networks (GNNs) provide a powerful modeling...

Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation

Graph Neural Networks (GNNs) are powerful to learn the representation of...

Learning Feature Matching via Matchable Keypoint-Assisted Graph Neural Network

Accurately matching local features between a pair of images is a challen...

Equivariant Graph Mechanics Networks with Constraints

Learning to reason about relations and dynamics over multiple interactin...

Neural Graph Databases

Graph databases (GDBs) enable processing and analysis of unstructured, c...

SEA: Graph Shell Attention in Graph Neural Networks

A common issue in Graph Neural Networks (GNNs) is known as over-smoothin...

How does over-squashing affect the power of GNNs?

Graph Neural Networks (GNNs) are the state-of-the-art model for machine ...