TPM: Transition Probability Matrix -- Graph Structural Feature based Embedding
This work addresses graph embedding for node classification and link prediction, offering a novel method that improves performance on these tasks.
The authors tackled the problem of extracting node features in graphs by proposing the Transition Probability Matrix (TPM) method, which uses random walks and anonymous walks to capture topological similarities, resulting in superior performance in node classification and link prediction tasks compared to state-of-the-art algorithms.
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.