Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213443340> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W3213443340 abstract "Graph neural networks have recently achieved remarkable success in representing graph-structured data, with rapid progress in both the node embedding and graph pooling methods. Yet, they mostly focus on capturing information from the nodes considering their connectivity, and not much work has been done in representing the edges, which are essential components of a graph. However, for tasks such as graph reconstruction and generation, as well as graph classification tasks for which the edges are important for discrimination, accurately representing edges of a given graph is crucial to the success of the graph representation learning. To this end, we propose a novel edge representation learning framework based on Dual Hypergraph Transformation (DHT), which transforms the edges of a graph into the nodes of a hypergraph. This dual hypergraph construction allows us to apply message-passing techniques for node representations to edges. After obtaining edge representations from the hypergraphs, we then cluster or drop edges to obtain holistic graph-level edge representations. We validate our edge representation learning method with hypergraphs on diverse graph datasets for graph representation and generation performance, on which our method largely outperforms existing graph representation learning methods. Moreover, our edge representation learning and pooling method also largely outperforms state-of-the-art graph pooling methods on graph classification, not only because of its accurate edge representation learning, but also due to its lossless compression of the nodes and removal of irrelevant edges for effective message-passing." @default.
- W3213443340 created "2021-11-22" @default.
- W3213443340 creator A5013449404 @default.
- W3213443340 creator A5018777306 @default.
- W3213443340 creator A5022124273 @default.
- W3213443340 creator A5049802181 @default.
- W3213443340 creator A5055644098 @default.
- W3213443340 creator A5070302452 @default.
- W3213443340 date "2021-06-30" @default.
- W3213443340 modified "2023-10-16" @default.
- W3213443340 title "Edge Representation Learning with Hypergraphs" @default.
- W3213443340 doi "https://doi.org/10.48550/arxiv.2106.15845" @default.
- W3213443340 hasPublicationYear "2021" @default.
- W3213443340 type Work @default.
- W3213443340 sameAs 3213443340 @default.
- W3213443340 citedByCount "1" @default.
- W3213443340 countsByYear W32134433402023 @default.
- W3213443340 crossrefType "posted-content" @default.
- W3213443340 hasAuthorship W3213443340A5013449404 @default.
- W3213443340 hasAuthorship W3213443340A5018777306 @default.
- W3213443340 hasAuthorship W3213443340A5022124273 @default.
- W3213443340 hasAuthorship W3213443340A5049802181 @default.
- W3213443340 hasAuthorship W3213443340A5055644098 @default.
- W3213443340 hasAuthorship W3213443340A5070302452 @default.
- W3213443340 hasBestOaLocation W32134433401 @default.
- W3213443340 hasConcept C114614502 @default.
- W3213443340 hasConcept C128115575 @default.
- W3213443340 hasConcept C132525143 @default.
- W3213443340 hasConcept C154945302 @default.
- W3213443340 hasConcept C203776342 @default.
- W3213443340 hasConcept C22149727 @default.
- W3213443340 hasConcept C2781221856 @default.
- W3213443340 hasConcept C33923547 @default.
- W3213443340 hasConcept C41008148 @default.
- W3213443340 hasConcept C59404180 @default.
- W3213443340 hasConcept C70437156 @default.
- W3213443340 hasConcept C80444323 @default.
- W3213443340 hasConceptScore W3213443340C114614502 @default.
- W3213443340 hasConceptScore W3213443340C128115575 @default.
- W3213443340 hasConceptScore W3213443340C132525143 @default.
- W3213443340 hasConceptScore W3213443340C154945302 @default.
- W3213443340 hasConceptScore W3213443340C203776342 @default.
- W3213443340 hasConceptScore W3213443340C22149727 @default.
- W3213443340 hasConceptScore W3213443340C2781221856 @default.
- W3213443340 hasConceptScore W3213443340C33923547 @default.
- W3213443340 hasConceptScore W3213443340C41008148 @default.
- W3213443340 hasConceptScore W3213443340C59404180 @default.
- W3213443340 hasConceptScore W3213443340C70437156 @default.
- W3213443340 hasConceptScore W3213443340C80444323 @default.
- W3213443340 hasLocation W32134433401 @default.
- W3213443340 hasOpenAccess W3213443340 @default.
- W3213443340 hasPrimaryLocation W32134433401 @default.
- W3213443340 hasRelatedWork W2961051133 @default.
- W3213443340 hasRelatedWork W2972858205 @default.
- W3213443340 hasRelatedWork W3051479560 @default.
- W3213443340 hasRelatedWork W3145941582 @default.
- W3213443340 hasRelatedWork W3173804797 @default.
- W3213443340 hasRelatedWork W3208308319 @default.
- W3213443340 hasRelatedWork W3213443340 @default.
- W3213443340 hasRelatedWork W4293686637 @default.
- W3213443340 hasRelatedWork W4307933185 @default.
- W3213443340 hasRelatedWork W4308164949 @default.
- W3213443340 isParatext "false" @default.
- W3213443340 isRetracted "false" @default.
- W3213443340 magId "3213443340" @default.
- W3213443340 workType "article" @default.