Collaborative Bi-Aggregation for Directed Graph Embedding

TL;DR

This paper introduces COBA, a novel directed graph embedding method that uses collaborative bi-directional aggregation with spatial graph convolution to improve representation learning, especially for low-degree nodes.

Contribution

The paper proposes a new collaborative bi-aggregation approach for directed graph embedding that effectively handles low or zero in/out degree nodes using spatial-based graph convolution.

Findings

COBA outperforms state-of-the-art methods on multiple real-world datasets.

The proposed aggregation strategies significantly improve embedding quality.

Extensive experiments validate the effectiveness of COBA in various tasks.

Abstract

Directed graphs model asymmetric relationships between nodes and research on directed graph embedding is of great significance in downstream graph analysis and inference. Learning source and target embedding of nodes separately to preserve edge asymmetry has become the dominant approach, but also poses challenge for learning representations of low or even zero in/out degree nodes that are ubiquitous in sparse graphs. In this paper, a collaborative bi-directional aggregation method (COBA) for directed graphs embedding is proposed by introducing spatial-based graph convolution. Firstly, the source and target embeddings of the central node are learned by aggregating from the counterparts of the source and target neighbors, respectively; Secondly, the source/target embeddings of the zero in/out degree central nodes are enhanced by aggregating the counterparts of opposite-directional neighbors (i.e. target/source neighbors); Finally, source and target embeddings of the same node are correlated to achieve collaborative aggregation. Extensive experiments on real-world datasets demonstrate that the COBA comprehensively outperforms state-of-the-art methods on multiple tasks and meanwhile validates the effectiveness of proposed aggregation strategies.