Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385484860> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4385484860 abstract "Recently, many works on Graph Neural Networks (GNNs) have been well developed for graph-level representation learning tasks and continuously improve graph classification accuracy. These works, however, mainly focus on the principle of different blocks of GNNs to strengthen their representation learning capability and pay less attention to the choice of a more appropriate loss function as learning objectives. In this paper, we aim to facilitate the representation learning process of any existing GNN frameworks by incorporating more task-oriented objectives. To this end, we propose approaches based on Laplacian eigenmaps to enhance the common-used cross-entropy loss, called LEELoss. Our study shows, with the property of Laplacian eigenmaps for classification problems, that utilizing the Laplacian eigenmaps as a regularizer in the original loss function can further enhance the performance of the graph-level learning tasks. Finally, via extensive experiments on popular benchmark datasets, we demonstrate that the proposed approach actually facilitates the classification performance on various GNN frameworks." @default.
- W4385484860 created "2023-08-03" @default.
- W4385484860 creator A5015817857 @default.
- W4385484860 creator A5033004319 @default.
- W4385484860 creator A5068898389 @default.
- W4385484860 creator A5073463615 @default.
- W4385484860 date "2023-06-18" @default.
- W4385484860 modified "2023-09-26" @default.
- W4385484860 title "Enhanced Loss Function based on Laplacian Eigenmaps for Graph Classification" @default.
- W4385484860 cites W1606637515 @default.
- W4385484860 cites W1986402779 @default.
- W4385484860 cites W2001141328 @default.
- W4385484860 cites W2008857988 @default.
- W4385484860 cites W2053186076 @default.
- W4385484860 cites W2079746361 @default.
- W4385484860 cites W2097308346 @default.
- W4385484860 cites W2147286743 @default.
- W4385484860 cites W2158469157 @default.
- W4385484860 cites W2612872092 @default.
- W4385484860 cites W2788919350 @default.
- W4385484860 cites W2899708459 @default.
- W4385484860 cites W2963084622 @default.
- W4385484860 cites W2965394851 @default.
- W4385484860 cites W3086452730 @default.
- W4385484860 cites W3102554291 @default.
- W4385484860 doi "https://doi.org/10.1109/ijcnn54540.2023.10191340" @default.
- W4385484860 hasPublicationYear "2023" @default.
- W4385484860 type Work @default.
- W4385484860 citedByCount "0" @default.
- W4385484860 crossrefType "proceedings-article" @default.
- W4385484860 hasAuthorship W4385484860A5015817857 @default.
- W4385484860 hasAuthorship W4385484860A5033004319 @default.
- W4385484860 hasAuthorship W4385484860A5068898389 @default.
- W4385484860 hasAuthorship W4385484860A5073463615 @default.
- W4385484860 hasConcept C106301342 @default.
- W4385484860 hasConcept C108583219 @default.
- W4385484860 hasConcept C115178988 @default.
- W4385484860 hasConcept C119857082 @default.
- W4385484860 hasConcept C121332964 @default.
- W4385484860 hasConcept C132525143 @default.
- W4385484860 hasConcept C13280743 @default.
- W4385484860 hasConcept C134306372 @default.
- W4385484860 hasConcept C154945302 @default.
- W4385484860 hasConcept C165700671 @default.
- W4385484860 hasConcept C17744445 @default.
- W4385484860 hasConcept C185798385 @default.
- W4385484860 hasConcept C190502265 @default.
- W4385484860 hasConcept C199539241 @default.
- W4385484860 hasConcept C205649164 @default.
- W4385484860 hasConcept C2776359362 @default.
- W4385484860 hasConcept C33923547 @default.
- W4385484860 hasConcept C41008148 @default.
- W4385484860 hasConcept C59404180 @default.
- W4385484860 hasConcept C62520636 @default.
- W4385484860 hasConcept C7948225 @default.
- W4385484860 hasConcept C80444323 @default.
- W4385484860 hasConcept C94625758 @default.
- W4385484860 hasConceptScore W4385484860C106301342 @default.
- W4385484860 hasConceptScore W4385484860C108583219 @default.
- W4385484860 hasConceptScore W4385484860C115178988 @default.
- W4385484860 hasConceptScore W4385484860C119857082 @default.
- W4385484860 hasConceptScore W4385484860C121332964 @default.
- W4385484860 hasConceptScore W4385484860C132525143 @default.
- W4385484860 hasConceptScore W4385484860C13280743 @default.
- W4385484860 hasConceptScore W4385484860C134306372 @default.
- W4385484860 hasConceptScore W4385484860C154945302 @default.
- W4385484860 hasConceptScore W4385484860C165700671 @default.
- W4385484860 hasConceptScore W4385484860C17744445 @default.
- W4385484860 hasConceptScore W4385484860C185798385 @default.
- W4385484860 hasConceptScore W4385484860C190502265 @default.
- W4385484860 hasConceptScore W4385484860C199539241 @default.
- W4385484860 hasConceptScore W4385484860C205649164 @default.
- W4385484860 hasConceptScore W4385484860C2776359362 @default.
- W4385484860 hasConceptScore W4385484860C33923547 @default.
- W4385484860 hasConceptScore W4385484860C41008148 @default.
- W4385484860 hasConceptScore W4385484860C59404180 @default.
- W4385484860 hasConceptScore W4385484860C62520636 @default.
- W4385484860 hasConceptScore W4385484860C7948225 @default.
- W4385484860 hasConceptScore W4385484860C80444323 @default.
- W4385484860 hasConceptScore W4385484860C94625758 @default.
- W4385484860 hasLocation W43854848601 @default.
- W4385484860 hasOpenAccess W4385484860 @default.
- W4385484860 hasPrimaryLocation W43854848601 @default.
- W4385484860 hasRelatedWork W1486896483 @default.
- W4385484860 hasRelatedWork W1583012050 @default.
- W4385484860 hasRelatedWork W1630142532 @default.
- W4385484860 hasRelatedWork W2298820818 @default.
- W4385484860 hasRelatedWork W2384465505 @default.
- W4385484860 hasRelatedWork W2389786622 @default.
- W4385484860 hasRelatedWork W2937381246 @default.
- W4385484860 hasRelatedWork W3011949883 @default.
- W4385484860 hasRelatedWork W4293369197 @default.
- W4385484860 hasRelatedWork W4385484860 @default.
- W4385484860 isParatext "false" @default.
- W4385484860 isRetracted "false" @default.
- W4385484860 workType "article" @default.