Matches in SemOpenAlex for { <https://semopenalex.org/work/W2916877453> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2916877453 abstract "With the rapid growth of online social networks and IoT networks, mining valuable knowledge from the graph data become important. Meanwhile, as machine learning algorithms show their powers in prediction, different machine learning algorithms are proposed for different applications, e.g., personal recommendation, price prediction, communication anomaly detection. However, it is challenging to extract network features from graph data as the inputs for machine learning algorithms. One of the promising approaches is to use graph embedding approach, which extracts the valuable information of networks from each node into low dimensional vectors. However, the graph embedding approaches on a large-scale network require tremendous training time. Therefore, in this paper, we propose NOde Differentiation for Graph Embedding (NODGE) to prioritize the nodes, while high priority nodes are allocated with more resources to train their representations. We also theoretically analyze the proposed NODGE. Experimental results show that the proposed method reduces the training time of state-of-the-art method by at least 30.7%." @default.
- W2916877453 created "2019-03-02" @default.
- W2916877453 creator A5022378488 @default.
- W2916877453 creator A5040050806 @default.
- W2916877453 creator A5040953635 @default.
- W2916877453 creator A5066336388 @default.
- W2916877453 date "2018-12-01" @default.
- W2916877453 modified "2023-09-25" @default.
- W2916877453 title "On Accelerating Multi-Layered Heterogeneous Network Embedding Learning" @default.
- W2916877453 cites W1512819151 @default.
- W2916877453 cites W1968164782 @default.
- W2916877453 cites W1996934732 @default.
- W2916877453 cites W2053186076 @default.
- W2916877453 cites W2096078889 @default.
- W2916877453 cites W2102848467 @default.
- W2916877453 cites W2145339207 @default.
- W2916877453 cites W2153579005 @default.
- W2916877453 cites W2156718197 @default.
- W2916877453 cites W2173520492 @default.
- W2916877453 cites W2251849926 @default.
- W2916877453 cites W2577946330 @default.
- W2916877453 cites W2743104969 @default.
- W2916877453 cites W2762491690 @default.
- W2916877453 cites W2766447205 @default.
- W2916877453 cites W2792901531 @default.
- W2916877453 cites W2949999304 @default.
- W2916877453 cites W2950577311 @default.
- W2916877453 cites W2962756421 @default.
- W2916877453 cites W2963073614 @default.
- W2916877453 cites W3104097132 @default.
- W2916877453 cites W2136040699 @default.
- W2916877453 doi "https://doi.org/10.1109/glocom.2018.8647392" @default.
- W2916877453 hasPublicationYear "2018" @default.
- W2916877453 type Work @default.
- W2916877453 sameAs 2916877453 @default.
- W2916877453 citedByCount "0" @default.
- W2916877453 crossrefType "proceedings-article" @default.
- W2916877453 hasAuthorship W2916877453A5022378488 @default.
- W2916877453 hasAuthorship W2916877453A5040050806 @default.
- W2916877453 hasAuthorship W2916877453A5040953635 @default.
- W2916877453 hasAuthorship W2916877453A5066336388 @default.
- W2916877453 hasConcept C119857082 @default.
- W2916877453 hasConcept C124101348 @default.
- W2916877453 hasConcept C127413603 @default.
- W2916877453 hasConcept C132525143 @default.
- W2916877453 hasConcept C154945302 @default.
- W2916877453 hasConcept C41008148 @default.
- W2916877453 hasConcept C41608201 @default.
- W2916877453 hasConcept C62611344 @default.
- W2916877453 hasConcept C66938386 @default.
- W2916877453 hasConcept C75564084 @default.
- W2916877453 hasConcept C80444323 @default.
- W2916877453 hasConceptScore W2916877453C119857082 @default.
- W2916877453 hasConceptScore W2916877453C124101348 @default.
- W2916877453 hasConceptScore W2916877453C127413603 @default.
- W2916877453 hasConceptScore W2916877453C132525143 @default.
- W2916877453 hasConceptScore W2916877453C154945302 @default.
- W2916877453 hasConceptScore W2916877453C41008148 @default.
- W2916877453 hasConceptScore W2916877453C41608201 @default.
- W2916877453 hasConceptScore W2916877453C62611344 @default.
- W2916877453 hasConceptScore W2916877453C66938386 @default.
- W2916877453 hasConceptScore W2916877453C75564084 @default.
- W2916877453 hasConceptScore W2916877453C80444323 @default.
- W2916877453 hasLocation W29168774531 @default.
- W2916877453 hasOpenAccess W2916877453 @default.
- W2916877453 hasPrimaryLocation W29168774531 @default.
- W2916877453 hasRelatedWork W2767117938 @default.
- W2916877453 hasRelatedWork W2796988304 @default.
- W2916877453 hasRelatedWork W2802785542 @default.
- W2916877453 hasRelatedWork W2902147406 @default.
- W2916877453 hasRelatedWork W2902862580 @default.
- W2916877453 hasRelatedWork W2916059024 @default.
- W2916877453 hasRelatedWork W2973230183 @default.
- W2916877453 hasRelatedWork W2997671625 @default.
- W2916877453 hasRelatedWork W3007075380 @default.
- W2916877453 hasRelatedWork W3086523504 @default.
- W2916877453 hasRelatedWork W3089200643 @default.
- W2916877453 hasRelatedWork W3105705953 @default.
- W2916877453 hasRelatedWork W3118486513 @default.
- W2916877453 hasRelatedWork W3128129382 @default.
- W2916877453 hasRelatedWork W3130747874 @default.
- W2916877453 hasRelatedWork W3137176540 @default.
- W2916877453 hasRelatedWork W3158951731 @default.
- W2916877453 hasRelatedWork W3196983225 @default.
- W2916877453 hasRelatedWork W3199352295 @default.
- W2916877453 hasRelatedWork W3210150671 @default.
- W2916877453 isParatext "false" @default.
- W2916877453 isRetracted "false" @default.
- W2916877453 magId "2916877453" @default.
- W2916877453 workType "article" @default.