Preprint Article Version 1 This version is not peer-reviewed

HIVEC: A Hierarchical Approach for Vector Representation Learning of Graphs

Version 1 : Received: 2 February 2018 / Approved: 4 February 2018 / Online: 4 February 2018 (10:52:50 CET)

How to cite: Patel, A.; Mathiraj, R.R.; Jai, M.; Singh, K.; Sivadasan, N.; Balasubramanian, V.N. HIVEC: A Hierarchical Approach for Vector Representation Learning of Graphs. Preprints 2018, 2018020023 (doi: 10.20944/preprints201802.0023.v1). Patel, A.; Mathiraj, R.R.; Jai, M.; Singh, K.; Sivadasan, N.; Balasubramanian, V.N. HIVEC: A Hierarchical Approach for Vector Representation Learning of Graphs. Preprints 2018, 2018020023 (doi: 10.20944/preprints201802.0023.v1).

Abstract

This paper presents a new method : HIVEC to learn latent vector representations of graphs in a manner that captures the semantic dependencies of sub-structures. The representations can then be used in machine learning algorithms for tasks such as graph classification, clustering etcetera. The method proposed is unsupervised and uses the information of co-occurrence of sub-structures. It introduces a notion of hierarchical embeddings that allows us to avoid repetitive learning of sub-structures for every new graph. As an alternative to deep learning methods, the edit distance similarity between sub-structures is also used to learn vector representations. We compare the performance of these methods against previous work.

Subject Areas

deep learning; graph kernels; unsupervised learning

Readers' Comments and Ratings (0)

Leave a public comment
Send a private comment to the author(s)
Rate this article
Views 0
Downloads 0
Comments 0
Metrics 0
Leave a public comment

×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.