Matches in SemOpenAlex for { <https://semopenalex.org/work/W2906943923> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2906943923 abstract "Graph similarity search is among the most important graph-based applications, e.g. finding the chemical compounds that are most similar to a query compound. Graph similarity computation, such as Graph Edit Distance (GED) and Maximum Common Subgraph (MCS), is the core operation of graph similarity search and many other applications, but very costly to compute in practice. Inspired by the recent success of neural network approaches to several graph applications, such as node or graph classification, we propose a novel neural network based approach to address this classic yet challenging graph problem, aiming to alleviate the computational burden while preserving a good performance. The proposed approach, called SimGNN, combines two strategies. First, we design a learnable embedding function that maps every graph into a vector, which provides a global summary of a graph. A novel attention mechanism is proposed to emphasize the important nodes with respect to a specific similarity metric. Second, we design a pairwise node comparison method to supplement the graph-level embeddings with fine-grained node-level information. Our model achieves better generalization on unseen graphs, and in the worst case runs in quadratic time with respect to the number of nodes in two graphs. Taking GED computation as an example, experimental results on three real graph datasets demonstrate the effectiveness and efficiency of our approach. Specifically, our model achieves smaller error rate and great time reduction compared against a series of baselines, including several approximation algorithms on GED computation, and many existing graph neural network based models. To the best of our knowledge, we are among the first to adopt neural networks to explicitly model the similarity between two graphs, and provide a new direction for future research on graph similarity computation and graph similarity search." @default.
- W2906943923 created "2019-01-11" @default.
- W2906943923 creator A5021611426 @default.
- W2906943923 creator A5025213473 @default.
- W2906943923 creator A5059053886 @default.
- W2906943923 creator A5060007972 @default.
- W2906943923 creator A5077716269 @default.
- W2906943923 creator A5085541837 @default.
- W2906943923 date "2019-01-30" @default.
- W2906943923 modified "2023-10-17" @default.
- W2906943923 title "SimGNN" @default.
- W2906943923 cites W1492230849 @default.
- W2906943923 cites W1597213869 @default.
- W2906943923 cites W181192379 @default.
- W2906943923 cites W1985514943 @default.
- W2906943923 cites W1989135657 @default.
- W2906943923 cites W2008857988 @default.
- W2906943923 cites W2012459404 @default.
- W2906943923 cites W2032338144 @default.
- W2906943923 cites W2039444222 @default.
- W2906943923 cites W2053841470 @default.
- W2906943923 cites W2139688603 @default.
- W2906943923 cites W2152618599 @default.
- W2906943923 cites W2170607286 @default.
- W2906943923 cites W2290847742 @default.
- W2906943923 cites W2393319904 @default.
- W2906943923 cites W2469060249 @default.
- W2906943923 cites W2528808155 @default.
- W2906943923 cites W2604795503 @default.
- W2906943923 cites W2780819581 @default.
- W2906943923 cites W2809343047 @default.
- W2906943923 cites W2962756421 @default.
- W2906943923 cites W3104097132 @default.
- W2906943923 cites W3105705953 @default.
- W2906943923 cites W4291474301 @default.
- W2906943923 cites W74055483 @default.
- W2906943923 cites W984076445 @default.
- W2906943923 doi "https://doi.org/10.1145/3289600.3290967" @default.
- W2906943923 hasPublicationYear "2019" @default.
- W2906943923 type Work @default.
- W2906943923 sameAs 2906943923 @default.
- W2906943923 citedByCount "151" @default.
- W2906943923 countsByYear W29069439232018 @default.
- W2906943923 countsByYear W29069439232019 @default.
- W2906943923 countsByYear W29069439232020 @default.
- W2906943923 countsByYear W29069439232021 @default.
- W2906943923 countsByYear W29069439232022 @default.
- W2906943923 countsByYear W29069439232023 @default.
- W2906943923 crossrefType "proceedings-article" @default.
- W2906943923 hasAuthorship W2906943923A5021611426 @default.
- W2906943923 hasAuthorship W2906943923A5025213473 @default.
- W2906943923 hasAuthorship W2906943923A5059053886 @default.
- W2906943923 hasAuthorship W2906943923A5060007972 @default.
- W2906943923 hasAuthorship W2906943923A5077716269 @default.
- W2906943923 hasAuthorship W2906943923A5085541837 @default.
- W2906943923 hasBestOaLocation W29069439231 @default.
- W2906943923 hasConcept C11413529 @default.
- W2906943923 hasConcept C132525143 @default.
- W2906943923 hasConcept C154945302 @default.
- W2906943923 hasConcept C184898388 @default.
- W2906943923 hasConcept C41008148 @default.
- W2906943923 hasConcept C45374587 @default.
- W2906943923 hasConcept C80444323 @default.
- W2906943923 hasConceptScore W2906943923C11413529 @default.
- W2906943923 hasConceptScore W2906943923C132525143 @default.
- W2906943923 hasConceptScore W2906943923C154945302 @default.
- W2906943923 hasConceptScore W2906943923C184898388 @default.
- W2906943923 hasConceptScore W2906943923C41008148 @default.
- W2906943923 hasConceptScore W2906943923C45374587 @default.
- W2906943923 hasConceptScore W2906943923C80444323 @default.
- W2906943923 hasFunder F4320306076 @default.
- W2906943923 hasFunder F4320337376 @default.
- W2906943923 hasLocation W29069439231 @default.
- W2906943923 hasOpenAccess W2906943923 @default.
- W2906943923 hasPrimaryLocation W29069439231 @default.
- W2906943923 hasRelatedWork W1554404894 @default.
- W2906943923 hasRelatedWork W2363897636 @default.
- W2906943923 hasRelatedWork W2400034772 @default.
- W2906943923 hasRelatedWork W2754490690 @default.
- W2906943923 hasRelatedWork W2854384722 @default.
- W2906943923 hasRelatedWork W2892310698 @default.
- W2906943923 hasRelatedWork W2906943923 @default.
- W2906943923 hasRelatedWork W2952888666 @default.
- W2906943923 hasRelatedWork W3099616117 @default.
- W2906943923 hasRelatedWork W4283806386 @default.
- W2906943923 isParatext "false" @default.
- W2906943923 isRetracted "false" @default.
- W2906943923 magId "2906943923" @default.
- W2906943923 workType "article" @default.