Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification

TL;DR

Graph Decipher introduces a transparent dual-attention GNN that clarifies message-passing mechanisms, improves interpretability, reduces computational load, and enhances performance in node classification tasks, including imbalanced datasets.

Contribution

The paper presents Graph Decipher, a novel transparent dual-attention GNN that investigates message-passing by focusing on graph structure and node attributes, with efficient computation and improved accuracy.

Findings

Achieves state-of-the-art performance on seven datasets.

Reduces computational burden compared to existing methods.

Effectively alleviates imbalanced node classification problems.

Abstract

Graph neural networks can be effectively applied to find solutions for many real-world problems across widely diverse fields. The success of graph neural networks is linked to the message-passing mechanism on the graph, however, the message-aggregating behavior is still not entirely clear in most algorithms. To improve functionality, we propose a new transparent network called Graph Decipher to investigate the message-passing mechanism by prioritizing in two main components: the graph structure and node attributes, at the graph, feature, and global levels on a graph under the node classification task. However, the computation burden now becomes the most significant issue because the relevance of both graph structure and node attributes are computed on a graph. In order to solve this issue, only relevant representative node attributes are extracted by graph feature filters, allowing calculations to be performed in a category-oriented manner. Experiments on seven datasets show that Graph Decipher achieves state-of-the-art performance while imposing a substantially lower computation burden under the node classification task. Additionally, since our algorithm has the ability to explore the representative node attributes by category, it is utilized to alleviate the imbalanced node classification problem on multi-class graph datasets.