Unsupervised Inductive Whole-Graph Embedding by Preserving Graph Proximity
Preprint
Abstract
We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity. Our approach, UGRAPHEMB, is a general framework that provides a novel means to performing graph-level embedding in a completely unsupervised and inductive manner. The learned neural network can be considered as a function that receives any graph as input, either seen or unseen in the training set, and transforms it into an embedding. A novel graph-level embedding generation mechanism called Multi-Scale Node Attention (MSNA), is proposed. Experiments on five real graph datasets show that UGRAPHEMB achieves competitive accuracy in the tasks of graph classification, similarity ranking, and graph visualization.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Similarity Search in Graph Databases: A Multi-Layered Indexing Approach2017
- Molecular graph convolutions: moving beyond fingerprintsJournal of Computer-Aided Molecular Design, 2016
- Structural Deep Network Embedding2016
- Approximation of graph edit distance based on Hausdorff matchingPattern Recognition, 2015
- Approximate graph edit distance computation by means of bipartite graph matchingImage and Vision Computing, 2009
- Comparison of descriptor spaces for chemical compound retrieval and classificationKnowledge and Information Systems, 2007
- Substructure similarity search in graph databases2005
- Laplacian Eigenmaps for Dimensionality Reduction and Data RepresentationNeural Computation, 2003
- A general framework for adaptive processing of data structuresIEEE Transactions on Neural Networks, 1998
- A graph distance metric based on the maximal common subgraphPattern Recognition Letters, 1998