Matches in SemOpenAlex for { <https://semopenalex.org/work/W2740731087> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2740731087 endingPage "3190" @default.
- W2740731087 startingPage "3182" @default.
- W2740731087 abstract "In this paper, we study the gradient boosted decision trees (GBDT) when the output space is high dimensional and sparse. For example, in multilabel classification, the output space is a L-dimensional 0/1 vector, where L is number of labels that can grow to millions and beyond in many modern applications. We show that vanilla GBDT can easily run out of memory or encounter near-forever running time in this regime, and propose a new GBDT variant, GBDT-SPARSE, to resolve this problem by employing L0 regularization. We then discuss in detail how to utilize this sparsity to conduct GBDT training, including splitting the nodes, computing the sparse residual, and predicting in sub-linear time. Finally, we apply our algorithm to extreme multilabel classification problems, and show that the proposed GBDT-SPARSE achieves an order of magnitude improvements in model size and prediction time over existing methods, while yielding similar performance." @default.
- W2740731087 created "2017-08-08" @default.
- W2740731087 creator A5001215167 @default.
- W2740731087 creator A5004541836 @default.
- W2740731087 creator A5010841999 @default.
- W2740731087 creator A5024120345 @default.
- W2740731087 creator A5063459703 @default.
- W2740731087 creator A5068664439 @default.
- W2740731087 date "2017-08-06" @default.
- W2740731087 modified "2023-10-04" @default.
- W2740731087 title "Gradient boosted decision trees for high dimensional sparse output" @default.
- W2740731087 cites W1540371141 @default.
- W2740731087 cites W1678356000 @default.
- W2740731087 cites W1834987204 @default.
- W2740731087 cites W2068074736 @default.
- W2740731087 cites W2070493638 @default.
- W2740731087 cites W2117756735 @default.
- W2740731087 cites W2125816831 @default.
- W2740731087 cites W2143045257 @default.
- W2740731087 cites W2169753597 @default.
- W2740731087 cites W2183087644 @default.
- W2740731087 cites W2350220533 @default.
- W2740731087 cites W2437817353 @default.
- W2740731087 cites W2461743311 @default.
- W2740731087 cites W2520348554 @default.
- W2740731087 cites W2553372643 @default.
- W2740731087 cites W2555194213 @default.
- W2740731087 cites W273955616 @default.
- W2740731087 cites W2912934387 @default.
- W2740731087 cites W2951440817 @default.
- W2740731087 cites W2952140663 @default.
- W2740731087 cites W3102476541 @default.
- W2740731087 hasPublicationYear "2017" @default.
- W2740731087 type Work @default.
- W2740731087 sameAs 2740731087 @default.
- W2740731087 citedByCount "29" @default.
- W2740731087 countsByYear W27407310872018 @default.
- W2740731087 countsByYear W27407310872019 @default.
- W2740731087 countsByYear W27407310872020 @default.
- W2740731087 countsByYear W27407310872021 @default.
- W2740731087 crossrefType "proceedings-article" @default.
- W2740731087 hasAuthorship W2740731087A5001215167 @default.
- W2740731087 hasAuthorship W2740731087A5004541836 @default.
- W2740731087 hasAuthorship W2740731087A5010841999 @default.
- W2740731087 hasAuthorship W2740731087A5024120345 @default.
- W2740731087 hasAuthorship W2740731087A5063459703 @default.
- W2740731087 hasAuthorship W2740731087A5068664439 @default.
- W2740731087 hasConcept C10229987 @default.
- W2740731087 hasConcept C111919701 @default.
- W2740731087 hasConcept C11413529 @default.
- W2740731087 hasConcept C120136583 @default.
- W2740731087 hasConcept C153180895 @default.
- W2740731087 hasConcept C154945302 @default.
- W2740731087 hasConcept C155512373 @default.
- W2740731087 hasConcept C2776135515 @default.
- W2740731087 hasConcept C2778572836 @default.
- W2740731087 hasConcept C41008148 @default.
- W2740731087 hasConcept C5481197 @default.
- W2740731087 hasConcept C84525736 @default.
- W2740731087 hasConceptScore W2740731087C10229987 @default.
- W2740731087 hasConceptScore W2740731087C111919701 @default.
- W2740731087 hasConceptScore W2740731087C11413529 @default.
- W2740731087 hasConceptScore W2740731087C120136583 @default.
- W2740731087 hasConceptScore W2740731087C153180895 @default.
- W2740731087 hasConceptScore W2740731087C154945302 @default.
- W2740731087 hasConceptScore W2740731087C155512373 @default.
- W2740731087 hasConceptScore W2740731087C2776135515 @default.
- W2740731087 hasConceptScore W2740731087C2778572836 @default.
- W2740731087 hasConceptScore W2740731087C41008148 @default.
- W2740731087 hasConceptScore W2740731087C5481197 @default.
- W2740731087 hasConceptScore W2740731087C84525736 @default.
- W2740731087 hasLocation W27407310871 @default.
- W2740731087 hasOpenAccess W2740731087 @default.
- W2740731087 hasPrimaryLocation W27407310871 @default.
- W2740731087 hasRelatedWork W1678356000 @default.
- W2740731087 hasRelatedWork W1834987204 @default.
- W2740731087 hasRelatedWork W193151672 @default.
- W2740731087 hasRelatedWork W1940008012 @default.
- W2740731087 hasRelatedWork W2068074736 @default.
- W2740731087 hasRelatedWork W21006490 @default.
- W2740731087 hasRelatedWork W2114315281 @default.
- W2740731087 hasRelatedWork W2114393161 @default.
- W2740731087 hasRelatedWork W2183087644 @default.
- W2740731087 hasRelatedWork W2359108789 @default.
- W2740731087 hasRelatedWork W2362855512 @default.
- W2740731087 hasRelatedWork W2437817353 @default.
- W2740731087 hasRelatedWork W2461743311 @default.
- W2740731087 hasRelatedWork W2520348554 @default.
- W2740731087 hasRelatedWork W2739996966 @default.
- W2740731087 hasRelatedWork W2743021690 @default.
- W2740731087 hasRelatedWork W2744136723 @default.
- W2740731087 hasRelatedWork W2768348081 @default.
- W2740731087 hasRelatedWork W2788125153 @default.
- W2740731087 hasRelatedWork W3102476541 @default.
- W2740731087 isParatext "false" @default.
- W2740731087 isRetracted "false" @default.
- W2740731087 magId "2740731087" @default.
- W2740731087 workType "article" @default.