Deep MinCut: Learning Node Embeddings by Detecting Communities

doi:10.1016/j.patcog.2022.109126

Deep MinCut: Learning Node Embeddings by Detecting Communities

2023-02-01

15

PRE

AI

Quoc Viet Hung Nguyen

DOI：10.1016/j.patcog.2022.109126

原文链接

原文求助

摘要

En 中文

We present Deep MinCut (DMC), an unsupervised approach to learn node embeddings for graph -structured data. It derives node representations based on their membership in communities. As such, the embeddings directly provide insights into the graph structure, so that a separate clustering step is no longer needed. DMC learns both, node embeddings and communities, simultaneously by minimizing the mincut loss , which captures the number of connections between communities. Striving for high scalabil-ity, we also propose a training process for DMC based on minibatches. We provide empirical evidence that the communities learned by DMC are meaningful and that the node embeddings are competitive in different node classification benchmarks. (c) 2022 Elsevier Ltd. All rights reserved.

Keyword:

Node embedding

Graph representation learning

Community detection

Interpretable machine learning

Deep MinCut: Learning Node Embeddings by Detecting Communities

摘要

期刊

机构