Adaptive Graph Neural Networks with Temporal Memory

Abstract

Graph neural networks (GNNs) have emerged as a powerful tool for analyzing and modeling complex relationships within graphs, finding applications in diverse fields like social network analysis, drug discovery, and computer vision. However, traditional GNN architectures often suffer from limitations in capturing long-range dependencies, hindering their ability to effectively represent and learn from intricate structural information. This paper introduces Adaptive Graph Neural Networks (AGNNs) with a novel temporal memory mechanism, designed to address this challenge. The AGNN dynamically updates the network's memory across time, allowing it to better incorporate past states into its current predictions. We demonstrate the effectiveness of this approach through extensive experiments on several benchmark graph datasets, showcasing significant improvements in performance, particularly in tasks requiring long-range dependency identification. The proposed method offers a fundamentally new approach to GNNs, pushing the boundaries of their ability to handle complex graph structures.