Deep linear graph attention model for attributed graph clustering

作者：

Highlights：

• Design a novel linear graph attention network for attributed graph clustering.

• An adaptive strategy to evaluate the smoothness of node representations is proposed.

• Get node representations with both local and global dissimilarity of smooth features.

摘要

•Design a novel linear graph attention network for attributed graph clustering.•An adaptive strategy to evaluate the smoothness of node representations is proposed.•Get node representations with both local and global dissimilarity of smooth features.

论文关键词：Attributed graph clustering,Linear model,Attention-based fusion,Graph neural network,Graph representation learning

论文评审过程：Received 19 August 2021, Revised 20 March 2022, Accepted 24 March 2022, Available online 31 March 2022, Version of Record 12 April 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.108665