Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035122597> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3035122597 abstract "Learning interpretable representations in an unsupervised setting is an important yet a challenging task. Existing unsupervised interpretable methods focus on extracting independent salient features from data. However they miss out the fact that the entanglement of salient features may also be informative. Acknowledging these entanglements can improve the interpretability, resulting in extraction of higher quality and a wider variety of salient features. In this paper, we propose a new method to enable Generative Adversarial Networks (GANs) to discover salient features that may be entangled in an informative manner, instead of extracting only disentangled features. Specifically, we propose a regularizer to punish the disagreement between the extracted feature interactions and a given dependency structure while training. We model these interactions using a Bayesian network, estimate the maximum likelihood parameters and calculate a negative likelihood score to measure the disagreement. Upon qualitatively and quantitatively evaluating the proposed method using both synthetic and real-world datasets, we show that our proposed regularizer guides GANs to learn representations with disentanglement scores competing with the state-of-the-art, while extracting a wider variety of salient features." @default.
- W3035122597 created "2020-06-19" @default.
- W3035122597 creator A5021847817 @default.
- W3035122597 creator A5032851065 @default.
- W3035122597 creator A5057114929 @default.
- W3035122597 creator A5061718239 @default.
- W3035122597 creator A5080738591 @default.
- W3035122597 date "2020-07-01" @default.
- W3035122597 modified "2023-10-14" @default.
- W3035122597 title "Learning Interpretable Representations with Informative Entanglements" @default.
- W3035122597 cites W1663973292 @default.
- W3035122597 cites W1994618660 @default.
- W3035122597 cites W2001226231 @default.
- W3035122597 cites W2107037917 @default.
- W3035122597 cites W2173520492 @default.
- W3035122597 cites W2753738274 @default.
- W3035122597 cites W2803390034 @default.
- W3035122597 cites W2883471708 @default.
- W3035122597 cites W2904507620 @default.
- W3035122597 cites W2962790223 @default.
- W3035122597 cites W2963847595 @default.
- W3035122597 cites W2963891243 @default.
- W3035122597 cites W2964201867 @default.
- W3035122597 doi "https://doi.org/10.24963/ijcai.2020/273" @default.
- W3035122597 hasPublicationYear "2020" @default.
- W3035122597 type Work @default.
- W3035122597 sameAs 3035122597 @default.
- W3035122597 citedByCount "2" @default.
- W3035122597 countsByYear W30351225972022 @default.
- W3035122597 countsByYear W30351225972023 @default.
- W3035122597 crossrefType "proceedings-article" @default.
- W3035122597 hasAuthorship W3035122597A5021847817 @default.
- W3035122597 hasAuthorship W3035122597A5032851065 @default.
- W3035122597 hasAuthorship W3035122597A5057114929 @default.
- W3035122597 hasAuthorship W3035122597A5061718239 @default.
- W3035122597 hasAuthorship W3035122597A5080738591 @default.
- W3035122597 hasBestOaLocation W30351225971 @default.
- W3035122597 hasConcept C107673813 @default.
- W3035122597 hasConcept C119857082 @default.
- W3035122597 hasConcept C136197465 @default.
- W3035122597 hasConcept C138885662 @default.
- W3035122597 hasConcept C153180895 @default.
- W3035122597 hasConcept C154945302 @default.
- W3035122597 hasConcept C19768560 @default.
- W3035122597 hasConcept C2776401178 @default.
- W3035122597 hasConcept C2780719617 @default.
- W3035122597 hasConcept C2781067378 @default.
- W3035122597 hasConcept C41008148 @default.
- W3035122597 hasConcept C41895202 @default.
- W3035122597 hasConcept C59404180 @default.
- W3035122597 hasConceptScore W3035122597C107673813 @default.
- W3035122597 hasConceptScore W3035122597C119857082 @default.
- W3035122597 hasConceptScore W3035122597C136197465 @default.
- W3035122597 hasConceptScore W3035122597C138885662 @default.
- W3035122597 hasConceptScore W3035122597C153180895 @default.
- W3035122597 hasConceptScore W3035122597C154945302 @default.
- W3035122597 hasConceptScore W3035122597C19768560 @default.
- W3035122597 hasConceptScore W3035122597C2776401178 @default.
- W3035122597 hasConceptScore W3035122597C2780719617 @default.
- W3035122597 hasConceptScore W3035122597C2781067378 @default.
- W3035122597 hasConceptScore W3035122597C41008148 @default.
- W3035122597 hasConceptScore W3035122597C41895202 @default.
- W3035122597 hasConceptScore W3035122597C59404180 @default.
- W3035122597 hasLocation W30351225971 @default.
- W3035122597 hasOpenAccess W3035122597 @default.
- W3035122597 hasPrimaryLocation W30351225971 @default.
- W3035122597 hasRelatedWork W2546942002 @default.
- W3035122597 hasRelatedWork W2774132622 @default.
- W3035122597 hasRelatedWork W2785535669 @default.
- W3035122597 hasRelatedWork W3006943036 @default.
- W3035122597 hasRelatedWork W3012234327 @default.
- W3035122597 hasRelatedWork W3191046242 @default.
- W3035122597 hasRelatedWork W4205364923 @default.
- W3035122597 hasRelatedWork W4206534706 @default.
- W3035122597 hasRelatedWork W4213225422 @default.
- W3035122597 hasRelatedWork W4229079080 @default.
- W3035122597 isParatext "false" @default.
- W3035122597 isRetracted "false" @default.
- W3035122597 magId "3035122597" @default.
- W3035122597 workType "article" @default.