Holistic Graph Neural Networks based on a global-based attention mechanism
作者：
Highlights：
• We propose the Holistic Graph Neural Network (HGNN) with a global-based attention mechanism.
• We also propose the Alpha Holistic Graph Neural Network a variant based on a hierarchical weighted aggregation mechanism.
• We test the proposed architecture on several benchmarks and achieve remarkable results.
• We investigate the best global graph pooling strategy which would enable our proposed architecture to gain in time and efficiency.
• We further demonstrate that other GNNs can greatly benefit from the addition of the global-based attention.
摘要
•We propose the Holistic Graph Neural Network (HGNN) with a global-based attention mechanism.•We also propose the Alpha Holistic Graph Neural Network a variant based on a hierarchical weighted aggregation mechanism.•We test the proposed architecture on several benchmarks and achieve remarkable results.•We investigate the best global graph pooling strategy which would enable our proposed architecture to gain in time and efficiency.•We further demonstrate that other GNNs can greatly benefit from the addition of the global-based attention.
论文关键词：Graph Neural Networks,Node representation,Graph classification,Global pooling
论文评审过程：Received 19 December 2020, Revised 25 December 2021, Accepted 30 December 2021, Available online 5 January 2022, Version of Record 20 January 2022.
论文官网地址：https://doi.org/10.1016/j.knosys.2021.108105
