Matches in SemOpenAlex for { <https://semopenalex.org/work/W3177925768> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3177925768 endingPage "6334" @default.
- W3177925768 startingPage "6321" @default.
- W3177925768 abstract "Traditional operations, e.g. graph edit distance (GED), are no longer suitable for processing the massive quantities of graph-structured data now available, due to their irregular structures and high computational complexities. With the advent of graph neural networks (GNNs), the problems of graph representation and graph similarity search have drawn particular attention in the field of computer vision. However, GNNs have been less studied for efficient and fast retrieval after graph representation. To represent graph-based data, and maintain fast retrieval while doing so, we introduce an efficient hash model with graph neural networks (HGNN) for a newly designed task (i.e. fast graph-based data retrieval). Due to its flexibility, HGNN can be implemented in both an unsupervised and supervised manner. Specifically, by adopting a graph neural network and hash learning algorithms, HGNN can effectively learn a similarity-preserving graph representation and compute pair-wise similarity or provide classification via low-dimensional compact hash codes. To the best of our knowledge, our model is the first to address graph hashing representation in the Hamming space. Our experimental results reach comparable prediction accuracy to full-precision methods and can even outperform traditional models in some cases. In real-world applications, using hash codes can greatly benefit systems with smaller memory capacities and accelerate the retrieval speed of graph-structured data. Hence, we believe the proposed HGNN has great potential in further research." @default.
- W3177925768 created "2021-07-19" @default.
- W3177925768 creator A5004792638 @default.
- W3177925768 creator A5036987388 @default.
- W3177925768 creator A5050181192 @default.
- W3177925768 creator A5063285882 @default.
- W3177925768 creator A5072833759 @default.
- W3177925768 creator A5082634513 @default.
- W3177925768 date "2021-01-01" @default.
- W3177925768 modified "2023-10-17" @default.
- W3177925768 title "Learning Efficient Hash Codes for Fast Graph-Based Data Similarity Retrieval" @default.
- W3177925768 cites W1489116628 @default.
- W3177925768 cites W1492230849 @default.
- W3177925768 cites W1566135517 @default.
- W3177925768 cites W181192379 @default.
- W3177925768 cites W1910300841 @default.
- W3177925768 cites W1974647172 @default.
- W3177925768 cites W1989135657 @default.
- W3177925768 cites W2003627696 @default.
- W3177925768 cites W2010541316 @default.
- W3177925768 cites W2012459404 @default.
- W3177925768 cites W2029205712 @default.
- W3177925768 cites W2112796928 @default.
- W3177925768 cites W2116341502 @default.
- W3177925768 cites W2164041127 @default.
- W3177925768 cites W2170607286 @default.
- W3177925768 cites W2411707397 @default.
- W3177925768 cites W2532962075 @default.
- W3177925768 cites W2558748708 @default.
- W3177925768 cites W2563399268 @default.
- W3177925768 cites W2577142429 @default.
- W3177925768 cites W2614818206 @default.
- W3177925768 cites W2781821509 @default.
- W3177925768 cites W2791083848 @default.
- W3177925768 cites W2906943923 @default.
- W3177925768 cites W2951041154 @default.
- W3177925768 cites W2963066159 @default.
- W3177925768 cites W2964333506 @default.
- W3177925768 cites W2967862025 @default.
- W3177925768 cites W2999606372 @default.
- W3177925768 cites W3088032605 @default.
- W3177925768 cites W3103152812 @default.
- W3177925768 cites W3105926539 @default.
- W3177925768 cites W4250060047 @default.
- W3177925768 doi "https://doi.org/10.1109/tip.2021.3093387" @default.
- W3177925768 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34224353" @default.
- W3177925768 hasPublicationYear "2021" @default.
- W3177925768 type Work @default.
- W3177925768 sameAs 3177925768 @default.
- W3177925768 citedByCount "2" @default.
- W3177925768 countsByYear W31779257682022 @default.
- W3177925768 crossrefType "journal-article" @default.
- W3177925768 hasAuthorship W3177925768A5004792638 @default.
- W3177925768 hasAuthorship W3177925768A5036987388 @default.
- W3177925768 hasAuthorship W3177925768A5050181192 @default.
- W3177925768 hasAuthorship W3177925768A5063285882 @default.
- W3177925768 hasAuthorship W3177925768A5072833759 @default.
- W3177925768 hasAuthorship W3177925768A5082634513 @default.
- W3177925768 hasConcept C132525143 @default.
- W3177925768 hasConcept C154945302 @default.
- W3177925768 hasConcept C176225458 @default.
- W3177925768 hasConcept C38652104 @default.
- W3177925768 hasConcept C41008148 @default.
- W3177925768 hasConcept C80444323 @default.
- W3177925768 hasConcept C99138194 @default.
- W3177925768 hasConceptScore W3177925768C132525143 @default.
- W3177925768 hasConceptScore W3177925768C154945302 @default.
- W3177925768 hasConceptScore W3177925768C176225458 @default.
- W3177925768 hasConceptScore W3177925768C38652104 @default.
- W3177925768 hasConceptScore W3177925768C41008148 @default.
- W3177925768 hasConceptScore W3177925768C80444323 @default.
- W3177925768 hasConceptScore W3177925768C99138194 @default.
- W3177925768 hasFunder F4320321001 @default.
- W3177925768 hasLocation W31779257681 @default.
- W3177925768 hasOpenAccess W3177925768 @default.
- W3177925768 hasPrimaryLocation W31779257681 @default.
- W3177925768 hasRelatedWork W11851375 @default.
- W3177925768 hasRelatedWork W2004949443 @default.
- W3177925768 hasRelatedWork W2492712819 @default.
- W3177925768 hasRelatedWork W2728035825 @default.
- W3177925768 hasRelatedWork W2913317685 @default.
- W3177925768 hasRelatedWork W2945002491 @default.
- W3177925768 hasRelatedWork W3111238704 @default.
- W3177925768 hasRelatedWork W3160133939 @default.
- W3177925768 hasRelatedWork W4288586756 @default.
- W3177925768 hasRelatedWork W4297790704 @default.
- W3177925768 hasVolume "30" @default.
- W3177925768 isParatext "false" @default.
- W3177925768 isRetracted "false" @default.
- W3177925768 magId "3177925768" @default.
- W3177925768 workType "article" @default.