Matches in SemOpenAlex for { <https://semopenalex.org/work/W2754865135> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2754865135 abstract "We present a novel and scalable label embedding framework for large-scale multi-label learning a.k.a ExMLDS (Extreme Multi-Label Learning using Distributional Semantics). Our approach draws inspiration from ideas rooted in distributional semantics, specifically the Skip Gram Negative Sampling (SGNS) approach, widely used to learn word embeddings for natural language processing tasks. Learning such embeddings can be reduced to a certain matrix factorization. Our approach is novel in that it highlights interesting connections between label embedding methods used for multi-label learning and paragraph/document embedding methods commonly used for learning representations of text data. The framework can also be easily extended to incorporate auxiliary information such as label-label correlations; this is crucial especially when there are a lot of missing labels in the training data. We demonstrate the effectiveness of our approach through an extensive set of experiments on a variety of benchmark datasets, and show that the proposed learning methods perform favorably compared to several baselines and state-of-the-art methods for large-scale multi-label learning. To facilitate end-to-end learning, we develop a joint learning algorithm that can learn the embeddings as well as a regression model that predicts these embeddings given input features, via efficient gradient-based methods." @default.
- W2754865135 created "2017-09-25" @default.
- W2754865135 creator A5017175274 @default.
- W2754865135 creator A5018765760 @default.
- W2754865135 creator A5029651089 @default.
- W2754865135 creator A5034432097 @default.
- W2754865135 creator A5051063821 @default.
- W2754865135 creator A5076826113 @default.
- W2754865135 date "2017-09-18" @default.
- W2754865135 modified "2023-09-26" @default.
- W2754865135 title "Leveraging Distributional Semantics for Multi-Label Learning" @default.
- W2754865135 cites W1940008012 @default.
- W2754865135 cites W2068074736 @default.
- W2754865135 cites W2125031621 @default.
- W2754865135 cites W2153579005 @default.
- W2754865135 cites W2153677638 @default.
- W2754865135 cites W2164278908 @default.
- W2754865135 cites W2250539671 @default.
- W2754865135 cites W2461743311 @default.
- W2754865135 cites W2744136723 @default.
- W2754865135 cites W2949249496 @default.
- W2754865135 cites W941230081 @default.
- W2754865135 hasPublicationYear "2017" @default.
- W2754865135 type Work @default.
- W2754865135 sameAs 2754865135 @default.
- W2754865135 citedByCount "0" @default.
- W2754865135 crossrefType "posted-content" @default.
- W2754865135 hasAuthorship W2754865135A5017175274 @default.
- W2754865135 hasAuthorship W2754865135A5018765760 @default.
- W2754865135 hasAuthorship W2754865135A5029651089 @default.
- W2754865135 hasAuthorship W2754865135A5034432097 @default.
- W2754865135 hasAuthorship W2754865135A5051063821 @default.
- W2754865135 hasAuthorship W2754865135A5076826113 @default.
- W2754865135 hasConcept C119857082 @default.
- W2754865135 hasConcept C130318100 @default.
- W2754865135 hasConcept C13280743 @default.
- W2754865135 hasConcept C154945302 @default.
- W2754865135 hasConcept C177264268 @default.
- W2754865135 hasConcept C184337299 @default.
- W2754865135 hasConcept C185798385 @default.
- W2754865135 hasConcept C199360897 @default.
- W2754865135 hasConcept C205649164 @default.
- W2754865135 hasConcept C2777462759 @default.
- W2754865135 hasConcept C2778828372 @default.
- W2754865135 hasConcept C41008148 @default.
- W2754865135 hasConcept C41608201 @default.
- W2754865135 hasConcept C48044578 @default.
- W2754865135 hasConcept C77088390 @default.
- W2754865135 hasConceptScore W2754865135C119857082 @default.
- W2754865135 hasConceptScore W2754865135C130318100 @default.
- W2754865135 hasConceptScore W2754865135C13280743 @default.
- W2754865135 hasConceptScore W2754865135C154945302 @default.
- W2754865135 hasConceptScore W2754865135C177264268 @default.
- W2754865135 hasConceptScore W2754865135C184337299 @default.
- W2754865135 hasConceptScore W2754865135C185798385 @default.
- W2754865135 hasConceptScore W2754865135C199360897 @default.
- W2754865135 hasConceptScore W2754865135C205649164 @default.
- W2754865135 hasConceptScore W2754865135C2777462759 @default.
- W2754865135 hasConceptScore W2754865135C2778828372 @default.
- W2754865135 hasConceptScore W2754865135C41008148 @default.
- W2754865135 hasConceptScore W2754865135C41608201 @default.
- W2754865135 hasConceptScore W2754865135C48044578 @default.
- W2754865135 hasConceptScore W2754865135C77088390 @default.
- W2754865135 hasLocation W27548651351 @default.
- W2754865135 hasOpenAccess W2754865135 @default.
- W2754865135 hasPrimaryLocation W27548651351 @default.
- W2754865135 hasRelatedWork W2129026672 @default.
- W2754865135 hasRelatedWork W2202571160 @default.
- W2754865135 hasRelatedWork W2397387607 @default.
- W2754865135 hasRelatedWork W2583789430 @default.
- W2754865135 hasRelatedWork W2711266013 @default.
- W2754865135 hasRelatedWork W2769358458 @default.
- W2754865135 hasRelatedWork W2790955120 @default.
- W2754865135 hasRelatedWork W2891932097 @default.
- W2754865135 hasRelatedWork W2903995686 @default.
- W2754865135 hasRelatedWork W3005067847 @default.
- W2754865135 hasRelatedWork W3017009006 @default.
- W2754865135 hasRelatedWork W3026763995 @default.
- W2754865135 hasRelatedWork W3106092787 @default.
- W2754865135 hasRelatedWork W3133448650 @default.
- W2754865135 hasRelatedWork W3169316096 @default.
- W2754865135 hasRelatedWork W3176520920 @default.
- W2754865135 hasRelatedWork W3183739743 @default.
- W2754865135 hasRelatedWork W3184603930 @default.
- W2754865135 hasRelatedWork W3200159660 @default.
- W2754865135 hasRelatedWork W3213432680 @default.
- W2754865135 isParatext "false" @default.
- W2754865135 isRetracted "false" @default.
- W2754865135 magId "2754865135" @default.
- W2754865135 workType "article" @default.