Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306317451> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4306317451 abstract "We study the weak supervision learning problem of Learning from Label Proportions (LLP) where the goal is to learn an instance-level classifier using proportions of various class labels in a bag -- a collection of input instances that often can be highly correlated. While representation learning for weakly-supervised tasks is found to be effective, they often require domain knowledge. To the best of our knowledge, representation learning for tabular data (unstructured data containing both continuous and categorical features) are not studied. In this paper, we propose to learn diverse representations of instances within the same bags to effectively utilize the weak bag-level supervision. We propose a domain agnostic LLP method, called Self Contrastive Representation Learning for LLP (SelfCLR-LLP) that incorporates a novel self--contrastive function as an auxiliary loss to learn representations on tabular data for LLP. We show that diverse representations for instances within the same bags aid efficient usage of the weak bag-level LLP supervision. We evaluate the proposed method through extensive experiments on real-world LLP datasets from e-commerce applications to demonstrate the effectiveness of our proposed SelfCLR-LLP. In this paper, we propose to learn diverse representations of instances within the same bags to effectively utilize the weak bag-level supervision. We propose a domain agnostic LLP method, called Self Contrastive Representation Learning for LLP (SelfCLR-LLP) that incorporates a novel self--contrastive function as an auxiliary loss to learn representations on tabular data for LLP. We show that diverse representations for instances within the same bags aid efficient usage of the weak bag-level LLP supervision. We evaluate the proposed method through extensive experiments on real-world LLP datasets from e-commerce applications to demonstrate the effectiveness of our proposed SelfCLR-LLP." @default.
- W4306317451 created "2022-10-16" @default.
- W4306317451 creator A5009374923 @default.
- W4306317451 creator A5011759026 @default.
- W4306317451 creator A5034432097 @default.
- W4306317451 creator A5038562115 @default.
- W4306317451 creator A5077772764 @default.
- W4306317451 creator A5084091166 @default.
- W4306317451 date "2022-10-17" @default.
- W4306317451 modified "2023-10-16" @default.
- W4306317451 title "Domain-Agnostic Contrastive Representations for Learning from Label Proportions" @default.
- W4306317451 cites W1976526581 @default.
- W4306317451 cites W2073601450 @default.
- W4306317451 cites W2103284199 @default.
- W4306317451 cites W2321533354 @default.
- W4306317451 cites W2326925005 @default.
- W4306317451 cites W2520742745 @default.
- W4306317451 cites W2754977407 @default.
- W4306317451 cites W2793768763 @default.
- W4306317451 cites W2953327099 @default.
- W4306317451 cites W3095746859 @default.
- W4306317451 cites W3101704389 @default.
- W4306317451 cites W3106375245 @default.
- W4306317451 cites W3214897310 @default.
- W4306317451 cites W343636949 @default.
- W4306317451 doi "https://doi.org/10.1145/3511808.3557293" @default.
- W4306317451 hasPublicationYear "2022" @default.
- W4306317451 type Work @default.
- W4306317451 citedByCount "1" @default.
- W4306317451 countsByYear W43063174512023 @default.
- W4306317451 crossrefType "proceedings-article" @default.
- W4306317451 hasAuthorship W4306317451A5009374923 @default.
- W4306317451 hasAuthorship W4306317451A5011759026 @default.
- W4306317451 hasAuthorship W4306317451A5034432097 @default.
- W4306317451 hasAuthorship W4306317451A5038562115 @default.
- W4306317451 hasAuthorship W4306317451A5077772764 @default.
- W4306317451 hasAuthorship W4306317451A5084091166 @default.
- W4306317451 hasBestOaLocation W43063174511 @default.
- W4306317451 hasConcept C119857082 @default.
- W4306317451 hasConcept C134306372 @default.
- W4306317451 hasConcept C14036430 @default.
- W4306317451 hasConcept C154945302 @default.
- W4306317451 hasConcept C17744445 @default.
- W4306317451 hasConcept C199539241 @default.
- W4306317451 hasConcept C204321447 @default.
- W4306317451 hasConcept C207685749 @default.
- W4306317451 hasConcept C2776359362 @default.
- W4306317451 hasConcept C33923547 @default.
- W4306317451 hasConcept C36503486 @default.
- W4306317451 hasConcept C41008148 @default.
- W4306317451 hasConcept C5274069 @default.
- W4306317451 hasConcept C59404180 @default.
- W4306317451 hasConcept C78458016 @default.
- W4306317451 hasConcept C86803240 @default.
- W4306317451 hasConcept C94625758 @default.
- W4306317451 hasConcept C95623464 @default.
- W4306317451 hasConceptScore W4306317451C119857082 @default.
- W4306317451 hasConceptScore W4306317451C134306372 @default.
- W4306317451 hasConceptScore W4306317451C14036430 @default.
- W4306317451 hasConceptScore W4306317451C154945302 @default.
- W4306317451 hasConceptScore W4306317451C17744445 @default.
- W4306317451 hasConceptScore W4306317451C199539241 @default.
- W4306317451 hasConceptScore W4306317451C204321447 @default.
- W4306317451 hasConceptScore W4306317451C207685749 @default.
- W4306317451 hasConceptScore W4306317451C2776359362 @default.
- W4306317451 hasConceptScore W4306317451C33923547 @default.
- W4306317451 hasConceptScore W4306317451C36503486 @default.
- W4306317451 hasConceptScore W4306317451C41008148 @default.
- W4306317451 hasConceptScore W4306317451C5274069 @default.
- W4306317451 hasConceptScore W4306317451C59404180 @default.
- W4306317451 hasConceptScore W4306317451C78458016 @default.
- W4306317451 hasConceptScore W4306317451C86803240 @default.
- W4306317451 hasConceptScore W4306317451C94625758 @default.
- W4306317451 hasConceptScore W4306317451C95623464 @default.
- W4306317451 hasLocation W43063174511 @default.
- W4306317451 hasOpenAccess W4306317451 @default.
- W4306317451 hasPrimaryLocation W43063174511 @default.
- W4306317451 hasRelatedWork W2087861452 @default.
- W4306317451 hasRelatedWork W2403788517 @default.
- W4306317451 hasRelatedWork W2471138382 @default.
- W4306317451 hasRelatedWork W2556319748 @default.
- W4306317451 hasRelatedWork W2568140311 @default.
- W4306317451 hasRelatedWork W2984205432 @default.
- W4306317451 hasRelatedWork W3087493185 @default.
- W4306317451 hasRelatedWork W3200179079 @default.
- W4306317451 hasRelatedWork W4206762304 @default.
- W4306317451 hasRelatedWork W4386106250 @default.
- W4306317451 isParatext "false" @default.
- W4306317451 isRetracted "false" @default.
- W4306317451 workType "article" @default.