Meta-Causal Feature Learning for Out-of-Distribution Generalization
Causal inference has become a powerful tool to handle the out-of-distribution (OOD) generalization problem, which aims to extract the invariant features. However, conventional methods apply causal learners from multiple data splits, which may incur biased representation learning from imbalanced data distributions and difficulty in invariant feature learning from heterogeneous sources. To address these issues, this paper presents a balanced meta-causal learner (BMCL), which includes a balanced task generation module (BTG) and a meta-causal feature learning module (MCFL). Specifically, the BTG module learns to generate balanced subsets by a self-learned partitioning algorithm with constraints on the proportions of sample classes and contexts. The MCFL module trains a meta-learner adapted to different distributions. Experiments conducted on NICO++ dataset verified that BMCL effectively identifies the class-invariant visual regions for classification and may serve as a general framework to improve the performance of the state-of-the-art methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Causal InferenceOut-of-Distribution GeneralizationRepresentation LearningSimilar Papers 제목 키워드 기반
RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning
Gradient-based meta-learning (GBML) algorithms are able to fast adapt to new tasks by transferring the learned meta-knowledge, while assuming that all tasks come from the same distribution (in-distribution, ID). However,…
Few-Shot Image Classificationimage-classificationImage ClassificationMeta-Learning+1Causality-inspired Latent Feature Augmentation for Single Domain Generalization
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 GeneralizationCausal-Symbolic Meta-Learning (CSML): Inducing Causal World Models for Few-Shot Generalization
Modern deep learning models excel at pattern recognition but remain fundamentally limited by their reliance on spurious correlations, leading to poor generalization and a demand for massive datasets. We argue that a key …
Causal InferenceMeta Learning not to Learn: Robustly Informing Meta-Learning under Nuisance-Varying Families
In settings where both spurious and causal predictors are available, standard neural networks trained under the objective of empirical risk minimization (ERM) with no additional inductive biases tend to have a dependence…
Meta-LearningSupercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer
Dealing with severe class imbalance poses a major challenge for real-world applications, especially when the accurate classification and generalization of minority classes is of primary interest. In computer vision, lear…
Inductive BiasTransfer Learning