TPM: Transition Probability Matrix -- Graph Structural Feature based Embedding

TL;DR

This paper introduces TPM, a novel graph embedding method using anonymous walks derived from random walks to better capture topological features, improving node classification and link prediction performance.

Contribution

The paper presents TPM, a new graph embedding technique that leverages anonymous walks for richer topological feature extraction, outperforming existing methods.

Findings

Superior performance in node classification tasks

Enhanced link prediction accuracy

Effective transfer of connectivity information to new graphs

Abstract

In this work, Transition Probability Matrix (TPM) is proposed as a new method for extracting the features of nodes in the graph. The proposed method uses random walks to capture the connectivity structure of a node's close neighborhood. The information obtained from random walks is converted to anonymous walks to extract the topological features of nodes. In the embedding process of nodes, anonymous walks are used since they capture the topological similarities of connectivities better than random walks. Therefore the obtained embedding vectors have richer information about the underlying connectivity structure. The method is applied to node classification and link prediction tasks. The performance of the proposed algorithm is superior to the state-of-the-art algorithms in the recent literature. Moreover, the extracted information about the connectivity structure of similar networks is used to link prediction and node classification tasks for a completely new graph.