Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034418897> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3034418897 abstract "Deep neural networks have gained great success in a broad range of tasks due to its remarkable capability to learn semantically rich features from high-dimensional data. However, they often require large-scale labelled data to successfully learn such features, which significantly hinders their adaption in unsupervised learning tasks, such as anomaly detection and clustering, and limits their applications to critical domains where obtaining massive labelled data is prohibitively expensive. To enable unsupervised learning on those domains, in this work we propose to learn features without using any labelled data by training neural networks to predict data distances in a randomly projected space. Random mapping is a theoretically proven approach to obtain approximately preserved distances. To well predict these distances, the representation learner is optimised to learn genuine class structures that are implicitly embedded in the randomly projected space. Empirical results on 19 real-world datasets show that our learned representations substantially outperform a few state-of-the-art methods for both anomaly detection and clustering tasks. Code is available at: url{https://git.io/RDP}" @default.
- W3034418897 created "2020-06-19" @default.
- W3034418897 creator A5006294869 @default.
- W3034418897 creator A5036455193 @default.
- W3034418897 creator A5039104219 @default.
- W3034418897 creator A5052220949 @default.
- W3034418897 date "2020-07-01" @default.
- W3034418897 modified "2023-10-12" @default.
- W3034418897 title "Unsupervised Representation Learning by Predicting Random Distances" @default.
- W3034418897 doi "https://doi.org/10.24963/ijcai.2020/408" @default.
- W3034418897 hasPublicationYear "2020" @default.
- W3034418897 type Work @default.
- W3034418897 sameAs 3034418897 @default.
- W3034418897 citedByCount "23" @default.
- W3034418897 countsByYear W30344188972021 @default.
- W3034418897 countsByYear W30344188972022 @default.
- W3034418897 countsByYear W30344188972023 @default.
- W3034418897 crossrefType "proceedings-article" @default.
- W3034418897 hasAuthorship W3034418897A5006294869 @default.
- W3034418897 hasAuthorship W3034418897A5036455193 @default.
- W3034418897 hasAuthorship W3034418897A5039104219 @default.
- W3034418897 hasAuthorship W3034418897A5052220949 @default.
- W3034418897 hasBestOaLocation W30344188971 @default.
- W3034418897 hasConcept C119857082 @default.
- W3034418897 hasConcept C124101348 @default.
- W3034418897 hasConcept C153180895 @default.
- W3034418897 hasConcept C154945302 @default.
- W3034418897 hasConcept C159985019 @default.
- W3034418897 hasConcept C177264268 @default.
- W3034418897 hasConcept C17744445 @default.
- W3034418897 hasConcept C192562407 @default.
- W3034418897 hasConcept C199360897 @default.
- W3034418897 hasConcept C199539241 @default.
- W3034418897 hasConcept C204323151 @default.
- W3034418897 hasConcept C2776359362 @default.
- W3034418897 hasConcept C2776760102 @default.
- W3034418897 hasConcept C2777212361 @default.
- W3034418897 hasConcept C41008148 @default.
- W3034418897 hasConcept C50644808 @default.
- W3034418897 hasConcept C59404180 @default.
- W3034418897 hasConcept C73555534 @default.
- W3034418897 hasConcept C739882 @default.
- W3034418897 hasConcept C8038995 @default.
- W3034418897 hasConcept C94625758 @default.
- W3034418897 hasConceptScore W3034418897C119857082 @default.
- W3034418897 hasConceptScore W3034418897C124101348 @default.
- W3034418897 hasConceptScore W3034418897C153180895 @default.
- W3034418897 hasConceptScore W3034418897C154945302 @default.
- W3034418897 hasConceptScore W3034418897C159985019 @default.
- W3034418897 hasConceptScore W3034418897C177264268 @default.
- W3034418897 hasConceptScore W3034418897C17744445 @default.
- W3034418897 hasConceptScore W3034418897C192562407 @default.
- W3034418897 hasConceptScore W3034418897C199360897 @default.
- W3034418897 hasConceptScore W3034418897C199539241 @default.
- W3034418897 hasConceptScore W3034418897C204323151 @default.
- W3034418897 hasConceptScore W3034418897C2776359362 @default.
- W3034418897 hasConceptScore W3034418897C2776760102 @default.
- W3034418897 hasConceptScore W3034418897C2777212361 @default.
- W3034418897 hasConceptScore W3034418897C41008148 @default.
- W3034418897 hasConceptScore W3034418897C50644808 @default.
- W3034418897 hasConceptScore W3034418897C59404180 @default.
- W3034418897 hasConceptScore W3034418897C73555534 @default.
- W3034418897 hasConceptScore W3034418897C739882 @default.
- W3034418897 hasConceptScore W3034418897C8038995 @default.
- W3034418897 hasConceptScore W3034418897C94625758 @default.
- W3034418897 hasLocation W30344188971 @default.
- W3034418897 hasLocation W30344188972 @default.
- W3034418897 hasLocation W30344188973 @default.
- W3034418897 hasOpenAccess W3034418897 @default.
- W3034418897 hasPrimaryLocation W30344188971 @default.
- W3034418897 hasRelatedWork W2997229301 @default.
- W3034418897 hasRelatedWork W3167013339 @default.
- W3034418897 hasRelatedWork W3174759195 @default.
- W3034418897 hasRelatedWork W3213069564 @default.
- W3034418897 hasRelatedWork W4230838436 @default.
- W3034418897 hasRelatedWork W4285233543 @default.
- W3034418897 hasRelatedWork W4287121366 @default.
- W3034418897 hasRelatedWork W4308619659 @default.
- W3034418897 hasRelatedWork W4386437125 @default.
- W3034418897 hasRelatedWork W60493759 @default.
- W3034418897 isParatext "false" @default.
- W3034418897 isRetracted "false" @default.
- W3034418897 magId "3034418897" @default.
- W3034418897 workType "article" @default.