FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3008760144> ?p ?o ?g. }

• W3008760144 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.
• W3008760144 created "2020-03-06" @default.
• W3008760144 creator A5021611426 @default.
• W3008760144 creator A5025213473 @default.
• W3008760144 creator A5046597133 @default.
• W3008760144 creator A5059053886 @default.
• W3008760144 creator A5077716269 @default.
• W3008760144 creator A5085541837 @default.
• W3008760144 date "2018-08-16" @default.
• W3008760144 modified "2023-09-26" @default.
• W3008760144 title "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" @default.
• W3008760144 cites W1579584928 @default.
• W3008760144 cites W1605556478 @default.
• W3008760144 cites W1647671624 @default.
• W3008760144 cites W181192379 @default.
• W3008760144 cites W1816257748 @default.
• W3008760144 cites W1985514943 @default.
• W3008760144 cites W1989135657 @default.
• W3008760144 cites W2008857988 @default.
• W3008760144 cites W2032338144 @default.
• W3008760144 cites W2039444222 @default.
• W3008760144 cites W2053841470 @default.
• W3008760144 cites W2078483536 @default.
• W3008760144 cites W2127426251 @default.
• W3008760144 cites W2139688603 @default.
• W3008760144 cites W2152618599 @default.
• W3008760144 cites W2170607286 @default.
• W3008760144 cites W2170738476 @default.
• W3008760144 cites W2173027866 @default.
• W3008760144 cites W2222512263 @default.
• W3008760144 cites W2299115575 @default.
• W3008760144 cites W2393319904 @default.
• W3008760144 cites W2469060249 @default.
• W3008760144 cites W2528808155 @default.
• W3008760144 cites W2554952599 @default.
• W3008760144 cites W2604314403 @default.
• W3008760144 cites W2604795503 @default.
• W3008760144 cites W2606202972 @default.
• W3008760144 cites W2615384791 @default.
• W3008760144 cites W2777863841 @default.
• W3008760144 cites W2780819581 @default.
• W3008760144 cites W2786016794 @default.
• W3008760144 cites W2787740662 @default.
• W3008760144 cites W2788178129 @default.
• W3008760144 cites W2799131379 @default.
• W3008760144 cites W2807009875 @default.
• W3008760144 cites W2808551187 @default.
• W3008760144 cites W2809343047 @default.
• W3008760144 cites W2811124557 @default.
• W3008760144 cites W2962756421 @default.
• W3008760144 cites W2962767366 @default.
• W3008760144 cites W2963460103 @default.
• W3008760144 cites W2964015378 @default.
• W3008760144 cites W2964121744 @default.
• W3008760144 cites W2964145825 @default.
• W3008760144 cites W2964311892 @default.
• W3008760144 cites W2964321699 @default.
• W3008760144 cites W3103995645 @default.
• W3008760144 cites W3104097132 @default.
• W3008760144 cites W74055483 @default.
• W3008760144 cites W984076445 @default.
• W3008760144 hasPublicationYear "2018" @default.
• W3008760144 type Work @default.
• W3008760144 sameAs 3008760144 @default.
• W3008760144 citedByCount "2" @default.
• W3008760144 countsByYear W30087601442020 @default.
• W3008760144 crossrefType "posted-content" @default.
• W3008760144 hasAuthorship W3008760144A5021611426 @default.
• W3008760144 hasAuthorship W3008760144A5025213473 @default.
• W3008760144 hasAuthorship W3008760144A5046597133 @default.
• W3008760144 hasAuthorship W3008760144A5059053886 @default.
• W3008760144 hasAuthorship W3008760144A5077716269 @default.
• W3008760144 hasAuthorship W3008760144A5085541837 @default.
• W3008760144 hasConcept C11413529 @default.
• W3008760144 hasConcept C132525143 @default.
• W3008760144 hasConcept C154945302 @default.
• W3008760144 hasConcept C17169500 @default.
• W3008760144 hasConcept C184898388 @default.
• W3008760144 hasConcept C203776342 @default.
• W3008760144 hasConcept C22149727 @default.
• W3008760144 hasConcept C41008148 @default.
• W3008760144 hasConcept C45374587 @default.
• W3008760144 hasConcept C80444323 @default.
• W3008760144 hasConceptScore W3008760144C11413529 @default.
• W3008760144 hasConceptScore W3008760144C132525143 @default.
• W3008760144 hasConceptScore W3008760144C154945302 @default.
• W3008760144 hasConceptScore W3008760144C17169500 @default.
• W3008760144 hasConceptScore W3008760144C184898388 @default.
• W3008760144 hasConceptScore W3008760144C203776342 @default.
• W3008760144 hasConceptScore W3008760144C22149727 @default.
• W3008760144 hasConceptScore W3008760144C41008148 @default.
• W3008760144 hasConceptScore W3008760144C45374587 @default.
• W3008760144 hasConceptScore W3008760144C80444323 @default.
• W3008760144 hasLocation W30087601441 @default.
• W3008760144 hasOpenAccess W3008760144 @default.
• W3008760144 hasPrimaryLocation W30087601441 @default.
• W3008760144 hasRelatedWork W1485714115 @default.
• W3008760144 hasRelatedWork W1509240356 @default.
• W3008760144 hasRelatedWork W1594224465 @default.
• W3008760144 hasRelatedWork W1605556478 @default.

• next