Graph U-Nets - PubMed
https://pubmed.ncbi.nlm.nih.gov/33999813Based on our proposed methods, we develop an encoder-decoder model, known as the graph U-Nets. Experimental results on node classification and graph classification tasks demonstrate that our methods achieve consistently better performance than previous models. Along this direction, we extend our methods by integrating attention mechanisms.
[1905.05178v1] Graph U-Nets - arXiv
https://arxiv.org/abs/1905.05178v111.05.2019 · Based on our proposed gPool and gUnpool layers, we develop an encoder-decoder model on graph, known as the graph U-Nets. Our experimental results on node classification and graph classification tasks demonstrate that our methods achieve consistently better performance than previous models. Submission history From: Hongyang Gao [ view email ]
Graph U-Nets | Papers With Code
paperswithcode.com › paper › graph-u-netsMay 11, 2019 · The gUnpool layer restores the graph into its original structure using the position information of nodes selected in the corresponding gPool layer. Based on our proposed gPool and gUnpool layers, we develop an encoder-decoder model on graph, known as the graph U-Nets. Our experimental results on node classification and graph classification ...
Graph U-Nets - PMLR
proceedings.mlr.press/v97/gao19a.html24.05.2019 · Based on our proposed gPool and gUnpool layers, we develop an encoder-decoder model on graph, known as the graph U-Nets. Our experimental results on node classification and graph classification tasks demonstrate that our methods achieve consistently better performance than previous models. Copy to Clipboard APA Gao, H. & Ji, S.. (2019).
GRAPH U-NET
openreview.net › pdfcorresponding graph unpooling (gUnpool) operation, which restores the graph to its original struc-ture with the help of locations of nodes selected in the corresponding gPool layer. Based on the gPool and gUnpool layers, we develop a graph U-Net, which allows high-level feature encoding and decoding for network embedding.