Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281640225> ?p ?o ?g. }
Showing items 1 to 43 of
43
with 100 items per page.
- W4281640225 abstract "We propose a novel and trainable graph unpooling layer for effective graph generation. Given a graph with features, the unpooling layer enlarges this graph and learns its desired new structure and features. Since this unpooling layer is trainable, it can be applied to graph generation either in the decoder of a variational autoencoder or in the generator of a generative adversarial network (GAN). We prove that the unpooled graph remains connected and any connected graph can be sequentially unpooled from a 3-nodes graph. We apply the unpooling layer within the GAN generator. Since the most studied instance of graph generation is molecular generation, we test our ideas in this context. Using the QM9 and ZINC datasets, we demonstrate the improvement obtained by using the unpooling layer instead of an adjacency-matrix-based approach." @default.
- W4281640225 created "2022-06-13" @default.
- W4281640225 creator A5056169947 @default.
- W4281640225 creator A5082971893 @default.
- W4281640225 creator A5088795209 @default.
- W4281640225 date "2022-06-03" @default.
- W4281640225 modified "2023-09-24" @default.
- W4281640225 title "An Unpooling Layer for Graph Generation" @default.
- W4281640225 doi "https://doi.org/10.48550/arxiv.2206.01874" @default.
- W4281640225 hasPublicationYear "2022" @default.
- W4281640225 type Work @default.
- W4281640225 citedByCount "0" @default.
- W4281640225 crossrefType "posted-content" @default.
- W4281640225 hasAuthorship W4281640225A5056169947 @default.
- W4281640225 hasAuthorship W4281640225A5082971893 @default.
- W4281640225 hasAuthorship W4281640225A5088795209 @default.
- W4281640225 hasBestOaLocation W42816402251 @default.
- W4281640225 hasConcept C11413529 @default.
- W4281640225 hasConcept C132525143 @default.
- W4281640225 hasConcept C180356752 @default.
- W4281640225 hasConcept C41008148 @default.
- W4281640225 hasConcept C80444323 @default.
- W4281640225 hasConceptScore W4281640225C11413529 @default.
- W4281640225 hasConceptScore W4281640225C132525143 @default.
- W4281640225 hasConceptScore W4281640225C180356752 @default.
- W4281640225 hasConceptScore W4281640225C41008148 @default.
- W4281640225 hasConceptScore W4281640225C80444323 @default.
- W4281640225 hasLocation W42816402251 @default.
- W4281640225 hasOpenAccess W4281640225 @default.
- W4281640225 hasPrimaryLocation W42816402251 @default.
- W4281640225 hasRelatedWork W1582690601 @default.
- W4281640225 hasRelatedWork W1997448565 @default.
- W4281640225 hasRelatedWork W2351491280 @default.
- W4281640225 hasRelatedWork W2371447506 @default.
- W4281640225 hasRelatedWork W2386767533 @default.
- W4281640225 hasRelatedWork W3034334914 @default.
- W4281640225 hasRelatedWork W303980170 @default.
- W4281640225 hasRelatedWork W3164207840 @default.
- W4281640225 hasRelatedWork W4293519063 @default.
- W4281640225 hasRelatedWork W4320342417 @default.
- W4281640225 isParatext "false" @default.
- W4281640225 isRetracted "false" @default.
- W4281640225 workType "article" @default.