Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376122953> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4376122953 abstract "Explainable recommender systems can explain their recommendation decisions, enhancing user trust in the systems. Most explainable recommender systems either rely on human-annotated rationales to train models for explanation generation or leverage the attention mechanism to extract important text spans from reviews as explanations. The extracted rationales are often confined to an individual review and may fail to identify the implicit features beyond the review text. To avoid the expensive human annotation process and to generate explanations beyond individual reviews, we propose to incorporate a geometric prior learnt from user-item interactions into a variational network which infers latent factors from user-item reviews. The latent factors from an individual user-item pair can be used for both recommendation and explanation generation, which naturally inherit the global characteristics encoded in the prior knowledge. Experimental results on three e-commerce datasets show that our model significantly improves the interpretability of a variational recommender using the Wasserstein distance while achieving performance comparable to existing content-based recommender systems in terms of recommendation behaviours." @default.
- W4376122953 created "2023-05-12" @default.
- W4376122953 creator A5009086593 @default.
- W4376122953 creator A5015709853 @default.
- W4376122953 creator A5016038041 @default.
- W4376122953 creator A5062168574 @default.
- W4376122953 creator A5070326893 @default.
- W4376122953 date "2023-05-09" @default.
- W4376122953 modified "2023-10-18" @default.
- W4376122953 title "Explainable Recommender with Geometric Information Bottleneck" @default.
- W4376122953 doi "https://doi.org/10.48550/arxiv.2305.05331" @default.
- W4376122953 hasPublicationYear "2023" @default.
- W4376122953 type Work @default.
- W4376122953 citedByCount "0" @default.
- W4376122953 crossrefType "posted-content" @default.
- W4376122953 hasAuthorship W4376122953A5009086593 @default.
- W4376122953 hasAuthorship W4376122953A5015709853 @default.
- W4376122953 hasAuthorship W4376122953A5016038041 @default.
- W4376122953 hasAuthorship W4376122953A5062168574 @default.
- W4376122953 hasAuthorship W4376122953A5070326893 @default.
- W4376122953 hasBestOaLocation W43761229531 @default.
- W4376122953 hasConcept C111919701 @default.
- W4376122953 hasConcept C119857082 @default.
- W4376122953 hasConcept C149635348 @default.
- W4376122953 hasConcept C153083717 @default.
- W4376122953 hasConcept C154945302 @default.
- W4376122953 hasConcept C23123220 @default.
- W4376122953 hasConcept C2780513914 @default.
- W4376122953 hasConcept C2781067378 @default.
- W4376122953 hasConcept C41008148 @default.
- W4376122953 hasConcept C557471498 @default.
- W4376122953 hasConcept C98045186 @default.
- W4376122953 hasConceptScore W4376122953C111919701 @default.
- W4376122953 hasConceptScore W4376122953C119857082 @default.
- W4376122953 hasConceptScore W4376122953C149635348 @default.
- W4376122953 hasConceptScore W4376122953C153083717 @default.
- W4376122953 hasConceptScore W4376122953C154945302 @default.
- W4376122953 hasConceptScore W4376122953C23123220 @default.
- W4376122953 hasConceptScore W4376122953C2780513914 @default.
- W4376122953 hasConceptScore W4376122953C2781067378 @default.
- W4376122953 hasConceptScore W4376122953C41008148 @default.
- W4376122953 hasConceptScore W4376122953C557471498 @default.
- W4376122953 hasConceptScore W4376122953C98045186 @default.
- W4376122953 hasLocation W43761229531 @default.
- W4376122953 hasOpenAccess W4376122953 @default.
- W4376122953 hasPrimaryLocation W43761229531 @default.
- W4376122953 hasRelatedWork W2605281151 @default.
- W4376122953 hasRelatedWork W3006943036 @default.
- W4376122953 hasRelatedWork W3012234327 @default.
- W4376122953 hasRelatedWork W3023163568 @default.
- W4376122953 hasRelatedWork W3119715496 @default.
- W4376122953 hasRelatedWork W3191046242 @default.
- W4376122953 hasRelatedWork W4205364923 @default.
- W4376122953 hasRelatedWork W4206534706 @default.
- W4376122953 hasRelatedWork W4229079080 @default.
- W4376122953 hasRelatedWork W4294031299 @default.
- W4376122953 isParatext "false" @default.
- W4376122953 isRetracted "false" @default.
- W4376122953 workType "article" @default.