Attention Models in Graphs: A Survey

TL;DR

This survey reviews the development of attention models in graph mining, categorizing existing approaches, discussing challenges, and outlining future research directions in graph attention mechanisms.

Contribution

It provides a comprehensive taxonomy and analysis of graph attention models, summarizing current methods and identifying open challenges for future research.

Findings

Introduces three taxonomies to categorize graph attention models

Analyzes various approaches based on problem setting, attention type, and task

Highlights key challenges and future directions in graph attention research

Abstract

Graph-structured data arise naturally in many different application domains. By representing data as graphs, we can capture entities (i.e., nodes) as well as their relationships (i.e., edges) with each other. Many useful insights can be derived from graph-structured data as demonstrated by an ever-growing body of work focused on graph mining. However, in the real-world, graphs can be both large - with many complex patterns - and noisy which can pose a problem for effective graph mining. An effective way to deal with this issue is to incorporate "attention" into graph mining solutions. An attention mechanism allows a method to focus on task-relevant parts of the graph, helping it to make better decisions. In this work, we conduct a comprehensive and focused survey of the literature on the emerging field of graph attention models. We introduce three intuitive taxonomies to group existing work. These are based on problem setting (type of input and output), the type of attention mechanism used, and the task (e.g., graph classification, link prediction, etc.). We motivate our taxonomies through detailed examples and use each to survey competing approaches from a unique standpoint. Finally, we highlight several challenges in the area and discuss promising directions for future work.