Matches in SemOpenAlex for { <https://semopenalex.org/work/W4375861821> ?p ?o ?g. }
- W4375861821 endingPage "34" @default.
- W4375861821 startingPage "1" @default.
- W4375861821 abstract "Many network applications can be formulated as NP-hard combinatorial optimization problems of community detection (CD) that partitions nodes of a graph into several groups with dense linkage. Most existing CD methods are transductive , which independently optimized their models for each single graph, and can only ensure either high quality or efficiency of CD by respectively using advanced machine learning techniques or fast heuristic approximation. In this study, we consider the CD task and aims to alleviate its NP-hard challenge. Motivated by the efficient inductive inference of graph neural networks (GNNs), we explore the possibility to achieve a better tradeoff between the quality and efficiency of CD via an inductive embedding scheme across multiple graphs of a system and propose a novel inductive community detection (ICD) method. Concretely, ICD first conducts the offline training of an adversarial dual GNN structure on historical graphs to capture key properties of a system. The trained model is then directly generalized to new graphs of the same system for online CD without additional optimization, where a better tradeoff between quality and efficiency can be achieved. Compared with existing inductive approaches, we develop a novel feature extraction module based on graph coarsening, which can efficiently extract informative feature inputs for GNNs. Moreover, our original designs of adversarial dual GNN and clustering regularization loss further enable ICD to capture permutation-invariant community labels in the offline training and help derive community-preserved embedding to support the high-quality online CD. Experiments on a set of benchmarks demonstrate that ICD can achieve a significant tradeoff between quality and efficiency over various baselines." @default.
- W4375861821 created "2023-05-10" @default.
- W4375861821 creator A5007808758 @default.
- W4375861821 creator A5031383697 @default.
- W4375861821 creator A5058412586 @default.
- W4375861821 creator A5067160123 @default.
- W4375861821 creator A5073139380 @default.
- W4375861821 date "2023-06-15" @default.
- W4375861821 modified "2023-10-02" @default.
- W4375861821 title "Towards a Better Tradeoff between Quality and Efficiency of Community Detection: An Inductive Embedding Method across Graphs" @default.
- W4375861821 cites W143174683 @default.
- W4375861821 cites W1971421925 @default.
- W4375861821 cites W2008857988 @default.
- W4375861821 cites W2016477260 @default.
- W4375861821 cites W2023655578 @default.
- W4375861821 cites W2047940964 @default.
- W4375861821 cites W2074739868 @default.
- W4375861821 cites W2088162437 @default.
- W4375861821 cites W2111708605 @default.
- W4375861821 cites W2119571791 @default.
- W4375861821 cites W2119998616 @default.
- W4375861821 cites W2131681506 @default.
- W4375861821 cites W2132914434 @default.
- W4375861821 cites W2135957668 @default.
- W4375861821 cites W2151936673 @default.
- W4375861821 cites W2156028561 @default.
- W4375861821 cites W2169148563 @default.
- W4375861821 cites W2294347342 @default.
- W4375861821 cites W2393319904 @default.
- W4375861821 cites W2405933695 @default.
- W4375861821 cites W2604942799 @default.
- W4375861821 cites W2744331595 @default.
- W4375861821 cites W2769458339 @default.
- W4375861821 cites W2789919274 @default.
- W4375861821 cites W2885142590 @default.
- W4375861821 cites W2905284068 @default.
- W4375861821 cites W2908500813 @default.
- W4375861821 cites W2945827377 @default.
- W4375861821 cites W2962756421 @default.
- W4375861821 cites W2964230360 @default.
- W4375861821 cites W2964297465 @default.
- W4375861821 cites W2966694634 @default.
- W4375861821 cites W2967474335 @default.
- W4375861821 cites W2972018851 @default.
- W4375861821 cites W3006206211 @default.
- W4375861821 cites W3007813770 @default.
- W4375861821 cites W3013775343 @default.
- W4375861821 cites W3037459886 @default.
- W4375861821 cites W3090161371 @default.
- W4375861821 cites W3099152386 @default.
- W4375861821 cites W3104097132 @default.
- W4375861821 cites W3108625061 @default.
- W4375861821 cites W3133823961 @default.
- W4375861821 cites W3142500413 @default.
- W4375861821 cites W3166056081 @default.
- W4375861821 cites W3194841521 @default.
- W4375861821 cites W3213104978 @default.
- W4375861821 cites W4220720005 @default.
- W4375861821 cites W4224312546 @default.
- W4375861821 cites W4288704342 @default.
- W4375861821 cites W4291474301 @default.
- W4375861821 cites W4312856860 @default.
- W4375861821 cites W4319998119 @default.
- W4375861821 doi "https://doi.org/10.1145/3596605" @default.
- W4375861821 hasPublicationYear "2023" @default.
- W4375861821 type Work @default.
- W4375861821 citedByCount "0" @default.
- W4375861821 crossrefType "journal-article" @default.
- W4375861821 hasAuthorship W4375861821A5007808758 @default.
- W4375861821 hasAuthorship W4375861821A5031383697 @default.
- W4375861821 hasAuthorship W4375861821A5058412586 @default.
- W4375861821 hasAuthorship W4375861821A5067160123 @default.
- W4375861821 hasAuthorship W4375861821A5073139380 @default.
- W4375861821 hasBestOaLocation W43758618211 @default.
- W4375861821 hasConcept C119857082 @default.
- W4375861821 hasConcept C121332964 @default.
- W4375861821 hasConcept C124101348 @default.
- W4375861821 hasConcept C132525143 @default.
- W4375861821 hasConcept C154945302 @default.
- W4375861821 hasConcept C173801870 @default.
- W4375861821 hasConcept C21308566 @default.
- W4375861821 hasConcept C24890656 @default.
- W4375861821 hasConcept C41008148 @default.
- W4375861821 hasConcept C41608201 @default.
- W4375861821 hasConcept C80444323 @default.
- W4375861821 hasConceptScore W4375861821C119857082 @default.
- W4375861821 hasConceptScore W4375861821C121332964 @default.
- W4375861821 hasConceptScore W4375861821C124101348 @default.
- W4375861821 hasConceptScore W4375861821C132525143 @default.
- W4375861821 hasConceptScore W4375861821C154945302 @default.
- W4375861821 hasConceptScore W4375861821C173801870 @default.
- W4375861821 hasConceptScore W4375861821C21308566 @default.
- W4375861821 hasConceptScore W4375861821C24890656 @default.
- W4375861821 hasConceptScore W4375861821C41008148 @default.
- W4375861821 hasConceptScore W4375861821C41608201 @default.
- W4375861821 hasConceptScore W4375861821C80444323 @default.
- W4375861821 hasIssue "9" @default.
- W4375861821 hasLocation W43758618211 @default.