subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs

Abstract

In this paper, we present subgraph2vec, a novel approach for learning latent representations of rooted subgraphs from large graphs inspired by recent advancements in Deep Learning and Graph Kernels. These latent representations encode semantic substructure dependencies in a continuous vector space, which is easily exploited by statistical models for tasks such as graph classification, clustering, link prediction and community detection. subgraph2vec leverages on local information obtained from neighbourhoods of nodes to learn their latent representations in an unsupervised fashion. We demonstrate that subgraph vectors learnt by our approach could be used in conjunction with classifiers such as CNNs, SVMs and relational data clustering algorithms to achieve significantly superior accuracies. Also, we show that the subgraph vectors could be used for building a deep learning variant of Weisfeiler-Lehman graph kernel. Our experiments on several benchmark and large-scale real-world datasets reveal that subgraph2vec achieves significant improvements in accuracies over existing graph kernels on both supervised and unsupervised learning tasks. Specifically, on two realworld program analysis tasks, namely, code clone and malware detection, subgraph2vec outperforms state-of-the-art kernels by more than 17% and 4%, respectively.

Cited by in corpus (27)

• struc2vec: Learning Node Representations from Structural Identity
• graph2vec: Learning Distributed Representations of Graphs
• VERSE: Versatile Graph Embeddings from Similarity Measures
• Strategies for Pre-training Graph Neural Networks
• On Proximity and Structural Role-based Embeddings in Networks: Misconceptions, Techniques, and Applications
• GEMSEC: Graph Embedding with Self Clustering
• DeepCas: an End-to-end Predictor of Information Cascades
• M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classification
• Network representation learning systematic review: ancestors and current development state
• DeepGraph: Graph Structure Predicts Network Growth
• Context-aware, Adaptive and Scalable Android Malware Detection through Online Learning (extended version)
• Relaxed Softmax for learning from Positive and Unlabeled data
• Distributed Representation of Subgraphs
• Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art
• Data Curation with Deep Learning [Vision]
• Beyond Ensemble Averages: Leveraging Climate Model Ensembles for Subseasonal Forecasting
• Sampling Subgraph Network with Application to Graph Classification
• Representation Learning for Spatial Graphs
• Adaptive Visibility Graph Neural Network and its Application in Modulation Classification
• Ego-CNN: Distributed, Egocentric Representations of Graphs for Detecting Critical Structures
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• Unsupervised Graph Representation by Periphery and Hierarchical Information Maximization
• Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning
• Prob2Vec: Mathematical Semantic Embedding for Problem Retrieval in Adaptive Tutoring
• A Concept-Centered Hypertext Approach to Case-Based Retrieval
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
• A Multi-view Context-aware Approach to Android Malware Detection and Malicious Code Localization