DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Moon, Il-Chul | - |
dc.contributor.advisor | 문일철 | - |
dc.contributor.author | Kim, Hyemi | - |
dc.date.accessioned | 2021-05-13T19:36:30Z | - |
dc.date.available | 2021-05-13T19:36:30Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=925048&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/284898 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 산업및시스템공학과, 2020.8,[iv, 30 :] | - |
dc.description.abstract | In causal graphs, inferring exogenous variables is required to identify the counterfactual effect from observations. Given that the exogenous variable is often latent in Bayesian network, the modelers have to assume the structure of exogenous variables in a causal graph, and its corresponding variational autoencoder. A frequent assumption is defining a single latent variable to absorb the entire exogenous uncertainty, but we claim that such structure cannot avoid the dilemma of 1) the biased sampling in the decoder learning and 2) the information loss to regularize the decoders of interventions. Our model resolves this dilemma by disentangling the exogenous uncertainty into two latent variables of 1) independent to interventions and 2) correlated to interventions without causality. Particularly, our disentangling approach will preserve the latent variable correlated to interventions in generating counterfactual cases. We show that our method estimates total effect and counterfactual effect without a complete causal graph. Our first application is generating counterfactual fair data for a fairness task. Our second application is generating the counterfactual image, which do not naturally occur in the dataset. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Causal Inference▼aCounterfactual effect▼aLatent Disentanglement▼aVariational Autoencoder▼aData Generation | - |
dc.subject | 인과 추론▼a반사실적 효과▼a잠재변수 분리▼a베리에이션 오토인코더▼a데이터 생성 | - |
dc.title | Counterfactual inference and counterfactual data generation through latent disentanglement | - |
dc.title.alternative | 잠재변수 분리를 통한 반사실적 추론 및 반사실적 데이터 생성 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :산업및시스템공학과, | - |
dc.contributor.alternativeauthor | 김혜미 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.