Jul 20, 2020 · We propose two novel global graph pooling methods based on second-order pooling; namely, bilinear mapping and attentional second-order pooling.
May 5, 2023 · In addition, compared to existing graph pooling methods, second-order pooling is able to use information from all nodes and collect second-order.
divelab/sopool: Second-Order Pooling for Graph Neural Networks - GitHub
github.com › divelab › sopool
This is the code for our paper "Second-Order Pooling for Graph Neural Networks". It is based on the code from GIN. Many thanks!
We propose two novel global graph pooling methods based on second-order pooling; namely, bilinear mapping and attentional second-order pooling.
Jun 1, 2023 · We show that direct use of second-order pooling with graph neural networks leads to practical problems. To overcome these problems, we propose ...
This work proposes two novel global graph pooling methods based on second-order pooling; namely, bilinear mapping and attentional second- order pooling.
In this paper, we propose a Multi-head Global Second-Order Pooling (MGSOP) framework, which utilizes rich statistics inherent in node feature outputted by GTNs.
In addition, compared to existing graph pooling methods, second-order pooling is able to use information from all nodes and collect second-order statistics, ...
Sep 16, 2024 · This review aims to summarize the existing graph pooling operators for GNNs and their representative applications in omics.
Mar 15, 2024 · We propose a SOPGRU model for hyperspectral image classification. We propose a CSFA mechanism to eliminate noisy spectral–spatial features.
Missing: Neural Networks.