Uniform pooling for graph networks
| Autor: | Dewen Hu, Jian Qin, Li Liu, Hui Shen |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Theoretical computer science
Graph embedding Computer science Pooling 02 engineering and technology graph pooling lcsh:Technology lcsh:Chemistry 03 medical and health sciences 0302 clinical medicine Graph classification 0202 electrical engineering electronic engineering information engineering General Materials Science Instrumentation lcsh:QH301-705.5 Fluid Flow and Transfer Processes non-euclidean structured signal lcsh:T Process Chemistry and Technology General Engineering graph classification Graph lcsh:QC1-999 Computer Science Applications lcsh:Biology (General) lcsh:QD1-999 lcsh:TA1-2040 020201 artificial intelligence & image processing lcsh:Engineering (General). Civil engineering (General) 030217 neurology & neurosurgery lcsh:Physics graph convolution network |
| Zdroj: | Applied Sciences Volume 10 Issue 18 Applied Sciences, Vol 10, Iss 6287, p 6287 (2020) |
| Popis: | The graph convolution network has received a lot of attention because it extends the convolution to non-Euclidean domains. However, the graph pooling method is still less concerned, which can learn coarse graph embedding to facilitate graph classification. Previous pooling methods were based on assigning a score to each node and then pooling only the highest-scoring nodes, which might throw away whole neighbourhoods of nodes and therefore information. Here, we proposed a novel pooling method UGPool with a new point-of-view on selecting nodes. UGPool learns node scores based on node features and uniformly pools neighboring nodes instead of top nodes in the score-space, resulting in a uniformly coarsened graph. In multiple graph classification tasks, including the protein graphs, the biological graphs and the brain connectivity graphs, we demonstrated that UGPool outperforms other graph pooling methods while maintaining high efficiency. Moreover, we also show that UGPool can be integrated with multiple graph convolution networks to effectively improve performance compared to no pooling. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|