Chaos Is a LADDER: Domain Generalization Beyond Invariance via Reweighting
Domain generalization (DG) aims to learn from multiple source domains and generalize to unseen target domains. Most DG methods pursue invariance: they seek a causal representation whose prediction rule is invariant across domains. This principle is effective when the causal mechanism is stable, but becomes restrictive when the domain itself modulates how causal content maps to the response. In this case, directly feeding domain style into the predictor can create misleading shortcuts, since style does not by itself cause the response. Yet the apparent chaos of multiple styles can become a ladder: style can locate the unseen target domain among source domains and guide which domain-dependent prediction rules should be trusted. We propose \emph{Latent Adaptive Domain Disentanglement and Environment Reweighting} (LADDER), a fixed-model DG pipeline that learns causal/style representations, freezes the encoders, fits source-specific classifiers, and uses an unlabeled target-domain covariate set only at inference to compute weights over these fixed classifiers, with no target labels or model-state updates. We establish theoretical guarantees for source reweighting and validate LADDER on simulations, FMoW, and a location-grouped iWildCam protocol, with gains in overall and group-averaged accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain GeneralizationSimilar Papers 제목 키워드 기반
Learning Subset-Shared Invariances for Domain Generalization with Mixture-of-Experts
Domain generalization (DG) aims to learn a model from one or more source domains that generalizes to an unseen target domain without accessing target data during training. A common approach enforces invariance of represe…
Domain GeneralizationChaos is a Ladder: A New Understanding of Contrastive Learning
Recently, contrastive learning has risen to be a promising approach for large-scale self-supervised learning. However, theoretical understanding of how it works is still unclear. In this paper, we propose a new guarantee…
Contrastive LearningSelf-Supervised LearningVariation Brownian Kernel Ladders
Claims about the benefit of depth depend on the complexity assigned to a representation. We introduce the \emph{Variation Brownian Kernel Ladder} (VBKL), a path-atomic function-space framework that separates nonlinear re…
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap
Recently, contrastive learning has risen to be a promising approach for large-scale self-supervised learning. However, theoretical understanding of how it works is still unclear. In this paper, we propose a new guarantee…
ARCContrastive LearningModel SelectionSelf-Supervised LearningAdversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization
Single Domain Generalization (SDG) aims to develop models capable of generalizing to unseen target domains using only one source domain, a task complicated by substantial domain shifts and limited data diversity. Existin…
Domain GeneralizationData Augmentation