Related papers: Repeated Environment Inference for Invariant Learn…

Machine Learning is becoming more prevalent in science and engineering, but many approaches do not provide meaningful uncertainty estimates and predictions may also violate known physical knowledge. We propose a Bayesian framework to embed…

The Invariant Risk Minimization (IRM) framework aims to learn invariant features from a set of environments for solving the out-of-distribution (OOD) generalization problem. The underlying assumption is that the causal components of the…

Learning models whose predictions are invariant under multiple environments is a promising approach for out-of-distribution generalization. Such models are trained to extract features $X_{\text{inv}}$ where the conditional distribution $Y…

We introduce a transfer learning framework for regression that leverages heterogeneous source domains to improve predictive performance in a data-scarce target domain. Our approach learns a conditional generative model separately for each…

Classifiers trained with Empirical Risk Minimization (ERM) tend to rely on attributes that have high spurious correlation with the target. This can degrade the performance on underrepresented (or 'minority') groups that lack these…

Clinical machine learning models are increasingly trained using large scale, multimodal foundation paradigms, yet deployment environments often differ systematically from the data generating settings used during training. Such shifts arise…

Bayesian experimental design (BED) has been used as a method for conducting efficient experiments based on Bayesian inference. The existing methods, however, mostly focus on maximizing the expected information gain (EIG); the cost of…

When learning from positive and unlabelled data, it is a strong assumption that the positive observations are randomly sampled from the distribution of $X$ conditional on $Y = 1$, where X stands for the feature and Y the label. Most…

Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true…

Referring to objects in a natural and unambiguous manner is crucial for effective human-robot interaction. Previous research on learning-based referring expressions has focused primarily on comprehension tasks, while generating referring…

This paper proposes an information-theoretic representation learning framework, named conditional information flow maximization, to extract noise-invariant sufficient representations for the input data and target task. It promotes the…

In this paper the problem of learning appropriate bias for an environment of related tasks is examined from a Bayesian perspective. The environment of related tasks is shown to be naturally modelled by the concept of an {\em objective}…

Imitation learning often needs a large demonstration set in order to handle the full range of situations that an agent might find itself in during deployment. However, collecting expert demonstrations can be expensive. Recent work in…

Existing learning from demonstration algorithms usually assume access to expert demonstrations. However, this assumption is limiting in many real-world applications since the collected demonstrations may be suboptimal or even consist of…

While model-based reinforcement learning (MBRL) improves sample efficiency by learning world models from raw observations, existing methods struggle to generalize across structurally similar scenes and remain vulnerable to spurious…

Deep classifiers are known to rely on spurious features $\unicode{x2013}$ patterns which are correlated with the target on the training data but not inherently relevant to the learning problem, such as the image backgrounds when classifying…

By inferring latent groups in the training data, recent works introduce invariant learning to the case where environment annotations are unavailable. Typically, learning group invariance under a majority/minority split is empirically shown…

Molecular representation learning lays the foundation for drug discovery. However, existing methods suffer from poor out-of-distribution (OOD) generalization, particularly when data for training and testing originate from different…

We study causal inference in a multi-environment setting, in which the functional relations for producing the variables from their direct causes remain the same across environments, while the distribution of exogenous noises may vary. We…

Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an…