paper-with-me

홈 › Papers

Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach

2023-12-15 · Ziliang Chen, Yongsen Zheng, Zhao-Rong Lai, Quanlong Guan, Liang Lin

Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels de-confounded from the environments, advancing the technical roadmap of out-of-distribution (OOD) generalization. Despite spotlights around, recent theoretical results verified that some causal features recovered by IRLs merely pretend domain-invariantly in the training environments but fail in unseen domains. The \emph{fake invariance} severely endangers OOD generalization since the trustful objective can not be diagnosed and existing causal surgeries are invalid to rectify. In this paper, we review a IRL family (InvRat) under the Partially and Fully Informative Invariant Feature Structural Causal Models (PIIF SCM /FIIF SCM) respectively, to certify their weaknesses in representing fake invariant features, then, unify their causal diagrams to propose ReStructured SCM (RS-SCM). RS-SCM can ideally rebuild the spurious and the fake invariant features simultaneously. Given this, we further develop an approach based on conditional mutual information with respect to RS-SCM, then rigorously rectify the spurious and fake invariant effects. It can be easily implemented by a small feature selection subnet introduced in the IRL family, which is alternatively optimized to achieve our goal. Experiments verified the superiority of our approach to fight against the fake invariant issue across a variety of OOD generalization benchmarks.

📄 PDF Abstract BibTeX arXiv:2312.09758

Code (0)

등록된 구현이 없습니다.

Tasks

feature selectionRepresentation Learning

Methods 이 논문이 사용한 방법론

Feature Selection Feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables,…

Similar Papers 제목 키워드 기반

Invariance & Causal Representation Learning: Prospects and Limitations

2023-12-06 · Simon Bing, jonas Wahl, Urmi Ninad, Jakob Runge

In causal models, a given mechanism is assumed to be invariant to changes of other mechanisms. While this principle has been utilized for inference in settings where the causal variables are observed, theoretical insight…

Representation Learning

Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms

2021-06-02 · Yunqi Wang, Furui Liu, Zhitang Chen, Qing Lian 외

Domain generalization aims to learn knowledge invariant across different distributions while semantically meaningful for downstream tasks from multiple source domains, to improve the model's generalization ability on uns…

Domain Generalization

Identifying Invariant Texture Violation for Robust Deepfake Detection

2020-12-19 · Xinwei Sun, Botong Wu, Wei Chen

Existing deepfake detection methods have reported promising in-distribution results, by accessing published large-scale dataset. However, due to the non-smooth synthesis method, the fake samples in this dataset may expos…

DeepFake DetectionFace Swapping

Causal Discovery using Model Invariance through Knockoff Interventions

2022-07-08 · Wasim Ahmad, Maha Shadaydeh, Joachim Denzler

Cause-effect analysis is crucial to understand the underlying mechanism of a system. We propose to exploit model invariance through interventions on the predictors to infer causality in nonlinear multivariate systems of …

Causal DiscoverymodelTime SeriesTime Series Analysis

Diagnosing and Rectifying Vision Models using Language

2023-02-08 · Yuhui Zhang, Jeff Z. HaoChen, Shih-Cheng Huang, Kuan-Chieh Wang 외

Recent multi-modal contrastive learning models have demonstrated the ability to learn an embedding space suitable for building strong vision classifiers, by leveraging the rich information in large-scale image-caption da…

Contrastive Learning