.png){kind=icon}
Return
Deep MinCut: Learning Node Embeddings by Detecting Communities
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.109126.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
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.
Keywords:
Node embedding
Graph representation learning
Community detection
Interpretable machine learning
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
Every node counts: Self-ensembling graph convolutional networks for semi-supervised learning.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveTinnitus Retraining Therapy (TRT) as a Method for Treatment of Tinnitus and Hyperacusis Patients
PREAI
ShareSaveA simple graph embedding for anomaly detection in a stream of heterogeneous labeled graphsPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveShareSaveShareSave
Towards interpretable and robust hand detection via pixel-wise predictionPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveShareSave
View more