Matches in SemOpenAlex for { <https://semopenalex.org/work/W3125955182> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3125955182 abstract "Graph Neural Networks (GNNs) become very popular for graph-related applications due to their superior performance. However, they have been shown to be computationally expensive in large scale settings, because their produced node embeddings have to be computed recursively, which scales exponentially with the number of layers. To address this issue, several sampling-based methods have recently been proposed to perform training on a subset of nodes while maintaining the fidelity of the trained model. In this work, we introduce a decoupled greedy learning method for GNNs (DGL-GNN) that, instead of sampling the input graph, decouples the GNN into smaller modules and associates each module with greedy auxiliary objectives. Our approach allows GNN layers to be updated during the training process without waiting for feedback from successor layers, thus making parallel GNN training possible. Our method achieves improved efficiency without significantly compromising model performances, which would be important for time or memory limited applications. Further, we propose a lazy-update scheme during training to further improve its efficiency. We empirically analyse our proposed DGL-GNN model, and demonstrate its effectiveness and superior efficiency through a range of experiments. Compared to the sampling-based acceleration, our model is more stable, and we do not have to trade-off between efficiency and accuracy. Finally, we note that while here we focus on comparing the decoupled approach as an alternative to other methods, it can also be regarded as complementary, for example, to sampling and other scalability-enhancing improvements of GNN training." @default.
- W3125955182 created "2021-02-01" @default.
- W3125955182 creator A5005117825 @default.
- W3125955182 creator A5014747023 @default.
- W3125955182 creator A5025213473 @default.
- W3125955182 creator A5077231313 @default.
- W3125955182 date "2021-05-04" @default.
- W3125955182 modified "2023-10-03" @default.
- W3125955182 title "Decoupled Greedy Learning of Graph Neural Networks" @default.
- W3125955182 hasPublicationYear "2021" @default.
- W3125955182 type Work @default.
- W3125955182 sameAs 3125955182 @default.
- W3125955182 citedByCount "0" @default.
- W3125955182 crossrefType "journal-article" @default.
- W3125955182 hasAuthorship W3125955182A5005117825 @default.
- W3125955182 hasAuthorship W3125955182A5014747023 @default.
- W3125955182 hasAuthorship W3125955182A5025213473 @default.
- W3125955182 hasAuthorship W3125955182A5077231313 @default.
- W3125955182 hasConcept C106131492 @default.
- W3125955182 hasConcept C11413529 @default.
- W3125955182 hasConcept C119857082 @default.
- W3125955182 hasConcept C132525143 @default.
- W3125955182 hasConcept C140779682 @default.
- W3125955182 hasConcept C154945302 @default.
- W3125955182 hasConcept C2776459999 @default.
- W3125955182 hasConcept C31972630 @default.
- W3125955182 hasConcept C41008148 @default.
- W3125955182 hasConcept C48044578 @default.
- W3125955182 hasConcept C51823790 @default.
- W3125955182 hasConcept C76155785 @default.
- W3125955182 hasConcept C77088390 @default.
- W3125955182 hasConcept C80444323 @default.
- W3125955182 hasConceptScore W3125955182C106131492 @default.
- W3125955182 hasConceptScore W3125955182C11413529 @default.
- W3125955182 hasConceptScore W3125955182C119857082 @default.
- W3125955182 hasConceptScore W3125955182C132525143 @default.
- W3125955182 hasConceptScore W3125955182C140779682 @default.
- W3125955182 hasConceptScore W3125955182C154945302 @default.
- W3125955182 hasConceptScore W3125955182C2776459999 @default.
- W3125955182 hasConceptScore W3125955182C31972630 @default.
- W3125955182 hasConceptScore W3125955182C41008148 @default.
- W3125955182 hasConceptScore W3125955182C48044578 @default.
- W3125955182 hasConceptScore W3125955182C51823790 @default.
- W3125955182 hasConceptScore W3125955182C76155785 @default.
- W3125955182 hasConceptScore W3125955182C77088390 @default.
- W3125955182 hasConceptScore W3125955182C80444323 @default.
- W3125955182 hasOpenAccess W3125955182 @default.
- W3125955182 hasRelatedWork W2618541429 @default.
- W3125955182 hasRelatedWork W2739542029 @default.
- W3125955182 hasRelatedWork W2798937790 @default.
- W3125955182 hasRelatedWork W2807434070 @default.
- W3125955182 hasRelatedWork W2807631648 @default.
- W3125955182 hasRelatedWork W2812009592 @default.
- W3125955182 hasRelatedWork W2901523331 @default.
- W3125955182 hasRelatedWork W2905272567 @default.
- W3125955182 hasRelatedWork W3005908409 @default.
- W3125955182 hasRelatedWork W3021848436 @default.
- W3125955182 hasRelatedWork W3102250788 @default.
- W3125955182 hasRelatedWork W3117969921 @default.
- W3125955182 hasRelatedWork W3130170441 @default.
- W3125955182 hasRelatedWork W3130774444 @default.
- W3125955182 hasRelatedWork W3139882736 @default.
- W3125955182 hasRelatedWork W3174448407 @default.
- W3125955182 hasRelatedWork W3181074959 @default.
- W3125955182 hasRelatedWork W3201150168 @default.
- W3125955182 hasRelatedWork W3206105267 @default.
- W3125955182 hasRelatedWork W3212868355 @default.
- W3125955182 isParatext "false" @default.
- W3125955182 isRetracted "false" @default.
- W3125955182 magId "3125955182" @default.
- W3125955182 workType "article" @default.