AttrE2vec: Unsupervised Attributed Edge Representation Learning
This work addresses the gap in learning edge representations for attributed networks, which is important for researchers and practitioners working with graph data.
The paper introduces AttrE2Vec, an unsupervised inductive method for learning low-dimensional vector representations for edges in attributed networks. This method effectively captures topological proximity, attribute affinity, and feature similarity of edges, leading to higher quality measures (AUC, accuracy) in downstream tasks like edge classification and clustering compared to contemporary approaches.
Representation learning has overcome the often arduous and manual featurization of networks through (unsupervised) feature learning as it results in embeddings that can apply to a variety of downstream learning tasks. The focus of representation learning on graphs has focused mainly on shallow (node-centric) or deep (graph-based) learning approaches. While there have been approaches that work on homogeneous and heterogeneous networks with multi-typed nodes and edges, there is a gap in learning edge representations. This paper proposes a novel unsupervised inductive method called AttrE2Vec, which learns a low-dimensional vector representation for edges in attributed networks. It systematically captures the topological proximity, attributes affinity, and feature similarity of edges. Contrary to current advances in edge embedding research, our proposal extends the body of methods providing representations for edges, capturing graph attributes in an inductive and unsupervised manner. Experimental results show that, compared to contemporary approaches, our method builds more powerful edge vector representations, reflected by higher quality measures (AUC, accuracy) in downstream tasks as edge classification and edge clustering. It is also confirmed by analyzing low-dimensional embedding projections.