graph2vec: Learning Distributed Representations of Graphs

TL;DR

This paper introduces graph2vec, an unsupervised neural embedding framework that learns fixed-length vector representations of entire graphs, improving graph classification and clustering performance over existing substructure-based methods.

Contribution

The paper presents a novel neural embedding method, graph2vec, for learning task-agnostic, data-driven graph representations applicable to various graph analytics tasks.

Findings

graph2vec outperforms substructure-based methods in classification accuracy

It achieves competitive results with state-of-the-art graph kernels

Embeddings are unsupervised and task-agnostic, suitable for multiple downstream tasks

Abstract

Recent works on representation learning for graph structured data predominantly focus on learning distributed representations of graph substructures such as nodes and subgraphs. However, many graph analytics tasks such as graph classification and clustering require representing entire graphs as fixed length feature vectors. While the aforementioned approaches are naturally unequipped to learn such representations, graph kernels remain as the most effective way of obtaining them. However, these graph kernels use handcrafted features (e.g., shortest paths, graphlets, etc.) and hence are hampered by problems such as poor generalization. To address this limitation, in this work, we propose a neural embedding framework named graph2vec to learn data-driven distributed representations of arbitrary sized graphs. graph2vec's embeddings are learnt in an unsupervised manner and are task agnostic. Hence, they could be used for any downstream task such as graph classification, clustering and even seeding supervised representation learning approaches. Our experiments on several benchmark and large real-world datasets show that graph2vec achieves significant improvements in classification and clustering accuracies over substructure representation learning approaches and are competitive with state-of-the-art graph kernels.