Which way? Direction-Aware Attributed Graph Embedding

TL;DR

This paper introduces DIAGRAM, a novel direction-aware graph embedding algorithm that integrates textual features and preserves edge directionality, improving performance across multiple network analysis tasks.

Contribution

The paper presents DIAGRAM, a multi-objective, text-enriched embedding method that jointly captures directionality, textual features, and context, outperforming existing baselines.

Findings

Significantly outperforms six state-of-the-art baselines on link prediction and network reconstruction.

Achieves comparable performance on node classification tasks.

Effectively preserves edge directionality and textual features in embeddings.

Abstract

Graph embedding algorithms are used to efficiently represent (encode) a graph in a low-dimensional continuous vector space that preserves the most important properties of the graph. One aspect that is often overlooked is whether the graph is directed or not. Most studies ignore the directionality, so as to learn high-quality representations optimized for node classification. On the other hand, studies that capture directionality are usually effective on link prediction but do not perform well on other tasks. This preliminary study presents a novel text-enriched, direction-aware algorithm called DIAGRAM , based on a carefully designed multi-objective model to learn embeddings that preserve the direction of edges, textual features and graph context of nodes. As a result, our algorithm does not have to trade one property for another and jointly learns high-quality representations for multiple network analysis tasks. We empirically show that DIAGRAM significantly outperforms six state-of-the-art baselines, both direction-aware and oblivious ones,on link prediction and network reconstruction experiments using two popular datasets. It also achieves a comparable performance on node classification experiments against these baselines using the same datasets.