subgraph2vec swMATH ID: 36496 Software Authors: Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu, Santhoshkumar Saminathan Description: subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs. 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 Homepage: https://arxiv.org/abs/1606.08928 Source Code: https://github.com/MLDroid/subgraph2vec_gensim Dependencies: Python Keywords: Machine Learning; arXiv_cs.LG; Artificial Intelligence; arXiv_cs.AI; Cryptography; Security; arXiv_cs.CR; arXiv_cs.SE; Subgraphs; Graph Kernels; Deep Learning; Representation Learning Related Software: node2vec; Python; FastDTW; RolX; struc2vec; SchNet; AFGen; LIBSVM; DeepWalk; graph2vec; t-SNE; word2vec Cited in: 2 Publications Standard Articles 1 Publication describing the Software Year subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu, Santhoshkumar Saminathan 2016 all top 5 Cited by 7 Authors 1 Jung, Jason J. 1 Kersting, Kristian 1 Kriege, Nils M. 1 Lee, O-Joun 1 Morris, Christopher 1 Mutzel, Petra 1 Neumann, Marion Cited in 2 Serials 1 Artificial Intelligence 1 Data Mining and Knowledge Discovery Cited in 2 Fields 2 Computer science (68-XX) 1 Combinatorics (05-XX) Citations by Year