Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037221460> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3037221460 abstract "Graph representation learning is gaining popularity in a wide range of applications, such as social networks analysis, computational biology, and recommender systems. However, different with positive results from many academic studies, applying graph neural networks (GNNs) in a real-world application is still challenging due to non-stationary environments. The underlying distribution of streaming data changes unexpectedly, resulting in different graph structures (a.k.a., concept drift). Therefore, it is essential to devise a robust graph learning technique so that the model does not overfit to the training graphs. In this work, we present Hop Sampling, a straightforward regularization method that can effectively prevent GNNs from overfishing. The hop sampling randomly selects the number of propagation steps rather than fixing it, and by doing so, it encourages the model to learn meaningful node representation for all intermediate propagation layers and to experience a variety of plausible graphs that are not in the training set. Particularly, we describe the use case of our method in recommender systems, a representative example of the real-world non-stationary case. We evaluated hop sampling on a large-scale real-world LINE dataset and conducted an online A/B/n test in LINE Coupon recommender systems of LINE Wallet Tab. Experimental results demonstrate that the proposed scheme improves the prediction accuracy of GNNs. We observed hop sampling provides 7.97% and 16.93% improvements for NDCG and MAP compared to non-regularized GNN models in our online service. Furthermore, models using hop sampling alleviate the oversmoothing issue in GNNs enabling a deeper model as well as more diversified representation." @default.
- W3037221460 created "2020-07-02" @default.
- W3037221460 creator A5009992526 @default.
- W3037221460 creator A5012265266 @default.
- W3037221460 creator A5061621910 @default.
- W3037221460 date "2020-06-26" @default.
- W3037221460 modified "2023-10-16" @default.
- W3037221460 title "Hop Sampling: A Simple Regularized Graph Learning for Non-Stationary Environments" @default.
- W3037221460 cites W1854214752 @default.
- W3037221460 cites W2069870183 @default.
- W3037221460 cites W2111094216 @default.
- W3037221460 cites W2114507260 @default.
- W3037221460 cites W2116341502 @default.
- W3037221460 cites W2146456494 @default.
- W3037221460 cites W2519887557 @default.
- W3037221460 cites W2624407581 @default.
- W3037221460 cites W2624431344 @default.
- W3037221460 cites W2779809129 @default.
- W3037221460 cites W2890703109 @default.
- W3037221460 cites W2894175828 @default.
- W3037221460 cites W2895976713 @default.
- W3037221460 cites W2900763475 @default.
- W3037221460 cites W2945827377 @default.
- W3037221460 cites W2962756421 @default.
- W3037221460 cites W2962767366 @default.
- W3037221460 cites W2963460103 @default.
- W3037221460 cites W2963695795 @default.
- W3037221460 cites W2963911286 @default.
- W3037221460 cites W2964114465 @default.
- W3037221460 cites W2970049362 @default.
- W3037221460 cites W2970971581 @default.
- W3037221460 cites W3040645928 @default.
- W3037221460 cites W3100848837 @default.
- W3037221460 cites W3103720336 @default.
- W3037221460 doi "https://doi.org/10.48550/arxiv.2006.14897" @default.
- W3037221460 hasPublicationYear "2020" @default.
- W3037221460 type Work @default.
- W3037221460 sameAs 3037221460 @default.
- W3037221460 citedByCount "2" @default.
- W3037221460 countsByYear W30372214602020 @default.
- W3037221460 crossrefType "posted-content" @default.
- W3037221460 hasAuthorship W3037221460A5009992526 @default.
- W3037221460 hasAuthorship W3037221460A5012265266 @default.
- W3037221460 hasAuthorship W3037221460A5061621910 @default.
- W3037221460 hasBestOaLocation W30372214601 @default.
- W3037221460 hasConcept C106131492 @default.
- W3037221460 hasConcept C119857082 @default.
- W3037221460 hasConcept C124101348 @default.
- W3037221460 hasConcept C132525143 @default.
- W3037221460 hasConcept C140779682 @default.
- W3037221460 hasConcept C154945302 @default.
- W3037221460 hasConcept C22019652 @default.
- W3037221460 hasConcept C25906391 @default.
- W3037221460 hasConcept C31258907 @default.
- W3037221460 hasConcept C31972630 @default.
- W3037221460 hasConcept C41008148 @default.
- W3037221460 hasConcept C50644808 @default.
- W3037221460 hasConcept C557471498 @default.
- W3037221460 hasConcept C80444323 @default.
- W3037221460 hasConceptScore W3037221460C106131492 @default.
- W3037221460 hasConceptScore W3037221460C119857082 @default.
- W3037221460 hasConceptScore W3037221460C124101348 @default.
- W3037221460 hasConceptScore W3037221460C132525143 @default.
- W3037221460 hasConceptScore W3037221460C140779682 @default.
- W3037221460 hasConceptScore W3037221460C154945302 @default.
- W3037221460 hasConceptScore W3037221460C22019652 @default.
- W3037221460 hasConceptScore W3037221460C25906391 @default.
- W3037221460 hasConceptScore W3037221460C31258907 @default.
- W3037221460 hasConceptScore W3037221460C31972630 @default.
- W3037221460 hasConceptScore W3037221460C41008148 @default.
- W3037221460 hasConceptScore W3037221460C50644808 @default.
- W3037221460 hasConceptScore W3037221460C557471498 @default.
- W3037221460 hasConceptScore W3037221460C80444323 @default.
- W3037221460 hasLocation W30372214601 @default.
- W3037221460 hasOpenAccess W3037221460 @default.
- W3037221460 hasPrimaryLocation W30372214601 @default.
- W3037221460 hasRelatedWork W1996541855 @default.
- W3037221460 hasRelatedWork W2953328427 @default.
- W3037221460 hasRelatedWork W2985459377 @default.
- W3037221460 hasRelatedWork W2989932438 @default.
- W3037221460 hasRelatedWork W3099765033 @default.
- W3037221460 hasRelatedWork W3175189414 @default.
- W3037221460 hasRelatedWork W4210794429 @default.
- W3037221460 hasRelatedWork W4213073923 @default.
- W3037221460 hasRelatedWork W4224929651 @default.
- W3037221460 hasRelatedWork W4362499066 @default.
- W3037221460 isParatext "false" @default.
- W3037221460 isRetracted "false" @default.
- W3037221460 magId "3037221460" @default.
- W3037221460 workType "article" @default.