MPXGAT: An Attention based Deep Learning Model for Multiplex Graphs Embedding
This addresses the limitation of existing graph embedding methods that are confined to single-layer graphs, offering a solution for domains requiring multiplex network analysis.
The paper tackles the problem of embedding multiplex graphs, which represent complex systems with multifaceted relationships, by introducing MPXGAT, an attention-based deep learning model that outperforms state-of-the-art algorithms on benchmark datasets.
Graph representation learning has rapidly emerged as a pivotal field of study. Despite its growing popularity, the majority of research has been confined to embedding single-layer graphs, which fall short in representing complex systems with multifaceted relationships. To bridge this gap, we introduce MPXGAT, an innovative attention-based deep learning model tailored to multiplex graph embedding. Leveraging the robustness of Graph Attention Networks (GATs), MPXGAT captures the structure of multiplex networks by harnessing both intra-layer and inter-layer connections. This exploitation facilitates accurate link prediction within and across the network's multiple layers. Our comprehensive experimental evaluation, conducted on various benchmark datasets, confirms that MPXGAT consistently outperforms state-of-the-art competing algorithms.