Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
This work addresses the challenge of learning graph embeddings without supervision for applications in graph analysis, though it appears incremental by building on existing graph representation methods.
The paper tackles the problem of graph-level representation learning by introducing UGRAPHEMB, a framework that embeds graphs into a vector space to preserve graph-graph proximity in an unsupervised and inductive manner, achieving competitive accuracy on tasks like graph classification and similarity ranking across five real datasets.
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.