Jan 14, 2022 · We propose a Compact GSL architecture by MI compression, named CoGSL. Specifically, two basic views are extracted from original graph as two inputs of the ...
Compact Graph Structure Learning via Mutual Information Compression (TheWebConf 2022) Paper Link: https://arxiv.org/abs/2201.05540
In this paper, we theoretically prove that if we optimize basic views and final view based on mutual information, and keep their perfor- mance on labels ...
This work proposes a novel multi-view graph representation learning model via structure-aware searching and coarsening (GRLsc) on GT architecture for graph ...
In essence, an optimal graph structure should only contain the information about tasks while compress redundant noise as much as possible, which is defined as " ...
Compact Graph Structure Learning via Mutual Information Compression ... Authors: Nian Liu; Xiao Wang; Lingfei Wu; Yu Chen; Xiaojie Guo; Chuan Shi. Funders. the ...
However, these approaches typically employ heuristic methods for selecting node pairs to rewire. Furthermore, graph transformers (GTs) [Chen et al., ...
OpenGSL is a comprehensive benchmark for Graph Structure Learning(GSL). GSL is a family of data-centric learning approaches which jointly optimize the graph ...
People also ask
What is graph structure learning?
What are graph based deep learning methods?
Compact Graph Structure Learning via Mutual Information Compression. CoRR abs/2201.05540 (2022); 2021. [c13]. view. electronic edition via DOI; unpaywalled ...