paper-with-me

Papers

Domain Generalization using Causal Matching

2020-06-12 · arXiv 2020 6 · Divyat Mahajan, Shruti Tople, Amit Sharma

In the domain generalization literature, a common objective is to learn representations independent of the domain after conditioning on the class label. We show that this objective is not sufficient: there exist counter-examples where a model fails to generalize to unseen domains even after satisfying class-conditional domain invariance. We formalize this observation through a structural causal model and show the importance of modeling within-class variations for generalization. Specifically, classes contain objects that characterize specific causal features, and domains can be interpreted as interventions on these objects that change non-causal features. We highlight an alternative condition: inputs across domains should have the same representation if they are derived from the same object. Based on this objective, we propose matching-based algorithms when base objects are observed (e.g., through data augmentation) and approximate the objective when objects are not observed (MatchDG). Our simple matching-based algorithms are competitive to prior work on out-of-domain accuracy for rotated MNIST, Fashion-MNIST, PACS, and Chest-Xray datasets. Our method MatchDG also recovers ground-truth object matches: on MNIST and Fashion-MNIST, top-10 matches from MatchDG have over 50% overlap with ground-truth matches.

📄 PDF Abstract BibTeX arXiv:2006.07500

Code (1)

microsoft/robustdg 공식 구현 pytorch

Tasks

Data AugmentationDomain GeneralizationRotated MNIST

Similar Papers 제목 키워드 기반

Using Interventions to Improve Out-of-Distribution Generalization of Text-Matching Recommendation Systems

2022-10-07 · Parikshit Bansal, Yashoteja Prabhu, Emre Kiciman, Amit Sharma

Given a user's input text, text-matching recommender systems output relevant items by comparing the input text to available items' description, such as product-to-product recommendation on e-commerce platforms. As users'…

Language ModellingOut-of-Distribution GeneralizationProduct RecommendationRecommendation Systems+1

A Shift in Perspective on Causality in Domain Generalization

2025-08-18 · Damian Machlanski, Stephanie Riley, Edward Moroshko, Kurt Butler 외 arxiv

The promise that causal modelling can lead to robust AI generalization has been challenged in recent work on domain generalization (DG) benchmarks. We revisit the claims of the causality and DG literature, reconciling ap…

Domain Generalization

Invariant Causal Mechanisms through Distribution Matching

2022-06-23 · Mathieu Chevalley, Charlotte Bunne, Andreas Krause, Stefan Bauer

Learning representations that capture the underlying data generating process is a key problem for data efficient and robust use of neural networks. One key property for robustness which the learned representation should …

Domain Generalization

Causality-inspired Latent Feature Augmentation for Single Domain Generalization

2024-06-10 · Jian Xu, Chaojie Ji, Yankai Cao, Ye Li 외

Single domain generalization (Single-DG) intends to develop a generalizable model with only one single training domain to perform well on other unknown target domains. Under the domain-hungry configuration, how to expand…

Domain Generalization

How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings?

2026-06-10 · Julia Kostin, Kasra Jalaldoust, Elias Bareinboim, Samory Kpotufe 외 arxiv

Machine learning models often degrade when they are deployed on a target distribution that differs from the source distributions they were trained on. Recent work in causality-based domain generalization has shown how sh…

Domain GeneralizationDomain Adaptation