paper-with-me

홈 › Papers

Latent Causal Invariant Model

2020-11-04 · Xinwei Sun, Botong Wu, Xiangyu Zheng, Chang Liu, Wei Chen, Tao Qin, Tie-Yan Liu

Current supervised learning can learn spurious correlation during the data-fitting process, imposing issues regarding interpretability, out-of-distribution (OOD) generalization, and robustness. To avoid spurious correlation, we propose a Latent Causal Invariance Model (LaCIM) which pursues causal prediction. Specifically, we introduce latent variables that are separated into (a) output-causative factors and (b) others that are spuriously correlated to the output via confounders, to model the underlying causal factors. We further assume the generating mechanisms from latent space to observed data to be causally invariant. We give the identifiable claim of such invariance, particularly the disentanglement of output-causative factors from others, as a theoretical guarantee for precise inference and avoiding spurious correlation. We propose a Variational-Bayesian-based method for estimation and to optimize over the latent space for prediction. The utility of our approach is verified by improved interpretability, prediction power on various OOD scenarios (including healthcare) and robustness on security.

📄 PDF Abstract BibTeX arXiv:2011.02203

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementmodelPrediction

Similar Papers 제목 키워드 기반

Learning Invariant Causal Mechanism from Vision-Language Models

2024-05-24 · Zeen Song, Siyu Zhao, Xingyu Zhang, Jiangmeng Li 외

Large-scale pre-trained vision-language models such as CLIP have been widely applied to a variety of downstream scenarios. In real-world applications, the CLIP model is often utilized in more diverse scenarios than those…

Causal InferenceDecision Making

Time Series Domain Adaptation via Latent Invariant Causal Mechanism

2025-02-23 · Ruichu Cai, Junxian Huang, Zhenhui Yang, Zijian Li 외

Time series domain adaptation aims to transfer the complex temporal dependence from the labeled source domain to the unlabeled target domain. Recent advances leverage the stable causal mechanism over observed variables t…

Domain AdaptationTime SeriesTime Series ClassificationVariational Inference

InvarGC: Invariant Granger Causality for Heterogeneous Interventional Time Series under Latent Confounding

2025-10-22 · Ziyi Zhang, Shaogang Ren, Xiaoning Qian, Nick Duffield arxiv

Granger causality is widely used for causal structure discovery in complex systems from multivariate time series data. Traditional Granger causality tests based on linear models often fail to detect even mild non-linear …

Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style

2021-06-08 · NeurIPS 2021 12 · Julius von Kügelgen, Yash Sharma, Luigi Gresele, Wieland Brendel 외

Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data …

Data AugmentationDisentanglementImage ClassificationRepresentation Learning+1

Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition

2022-04-17 · Yingjie Chen, Diqi Chen, Tao Wang, Yizhou Wang 외

Subject-invariant facial action unit (AU) recognition remains challenging for the reason that the data distribution varies among subjects. In this paper, we propose a causal inference framework for subject-invariant faci…

Causal InferenceFacial Action Unit Detection