Traditional machine learning paradigms are based on the assumption that both training and test data follow the same statistical pattern, which is mathematically referred to as Independent and Identically Distributed ($i.i.d.$). However, in real-world applications, this $i.i.d.$ assumption often fails to hold due to unforeseen distributional shifts, leading to considerable degradation in model performance upon deployment. This observed discrepancy indicates the significance of investigating the Out-of-Distribution (OOD) generalization problem. OOD generalization is an emerging topic of machine learning research that focuses on complex scenarios wherein the distributions of the test data differ from those of the training data. This paper represents the first comprehensive, systematic review of OOD generalization, encompassing a spectrum of aspects from problem definition, methodological development, and evaluation procedures, to the implications and future directions of the field. Our discussion begins with a precise, formal characterization of the OOD generalization problem. Following that, we categorize existing methodologies into three segments: unsupervised representation learning, supervised model learning, and optimization, according to their positions within the overarching learning process. We provide an in-depth discussion on representative methodologies for each category, further elucidating the theoretical links between them. Subsequently, we outline the prevailing benchmark datasets employed in OOD generalization studies. To conclude, we overview the existing body of work in this domain and suggest potential avenues for future research on OOD generalization. A summary of the OOD generalization methodologies surveyed in this paper can be accessed at http://out-of-distribution-generalization.com.

The performance of predictive models has been observed to degrade under distribution shifts in a wide range of applications, such as healthcare [8, 68, 56, 67], economics [28, 18], education [5], vision [55, 47, 64, 70], and language [46, 6]. Distribution shifts vary in type, typically defined as either a change in the marginal distribution of the covariates (X-shifts), or changes in the conditional relationship between the outcome and covariate (Y |X-shifts). Real-world scenarios comprise of both types of shifts. In computer vision [46, 37, 60, 30, 72], Y |X-shifts are less likely as Y is constructed from human labels given an input X. Due to the prevalence of X-shifts, the implicit goal of many researchers is to develop a single robust model that can generalize effectively across multiple domains, akin to humans. For tabular data, Y |X-shifts may arise because of missing variables and hidden confounders. For example, the prevalence of diseases among patients may be affected by covariates that are not recorded in medical datasets but vary among individuals, such as lifestyle factors (e.g., diet, exercise, smoking status) and socioeconomic status [31, 74, 67]. Under Y |X-shifts, there may be a fundamental trade-off between learning algorithms: to perform well on a target distribution, a model may have to necessarily perform worse on others. Algorithmically, typical methods for addressing Y |X-shifts include distributionally robust optimization (DRO) [11, 63, 21, 59, 20] and causal learning methods [54, 7, 62, 36].

Domain generalization aims to solve the challenge of Out-of-Distribution (OOD) generalization by leveraging common knowledge learned from multiple training domains to generalize to unseen test domains. To accurately evaluate the OOD generalization ability, it is necessary to ensure that test data information is unavailable. However, the current domain generalization protocol may still have potential test data information leakage. This paper examines the potential risks of test data information leakage in two aspects of the current protocol: pretraining on ImageNet and oracle model selection. We propose that training from scratch and using multiple test domains would result in a more precise evaluation of OOD generalization ability. We also rerun the algorithms with the modified protocol and introduce a new leaderboard to encourage future research in domain generalization with a fairer comparison.

To ensure the out-of-distribution (OOD) generalization performance, traditional domain generalization (DG) methods resort to training on data from multiple sources with different underlying distributions. And the success of those DG methods largely depends on the fact that there are diverse training distributions. However, it usually needs great efforts to obtain enough heterogeneous data due to the high expenses, privacy issues or the scarcity of data. Thus an interesting yet seldom investigated problem arises: how to improve the OOD generalization performance when the perceived heterogeneity is limited. In this paper, we instantiate a new framework called few-domain generalization (FDG), which aims to learn a generalizable model from very few domains of novel tasks with the knowledge acquired from previous learning experiences on base tasks. Moreover, we propose a Meta Adaptive Task Sampling (MATS) procedure to differentiate base tasks according to their semantic and domain-shift similarity to the novel task. Empirically, we show that the newly introduced FDG framework can substantially improve the OOD generalization performance on the novel task and further combining MATS with episodic training could outperform several state-of-the-art DG baselines on widely used benchmarks like PACS and DomainNet.

Massive amounts of data are the foundation of data-driven recommendation models. As an inherent nature of big data, data heterogeneity widely exists in real-world recommendation systems. It reflects the differences in the properties among sub-populations. Ignoring the heterogeneity in recommendation data could limit the performance of recommendation models, hurt the sub-populational robustness, and make the models misled by biases. However, data heterogeneity has not attracted substantial attention in the recommendation community. Therefore, it inspires us to adequately explore and exploit heterogeneity for solving the above problems and assisting data analysis. In this work, we focus on exploring two representative categories of heterogeneity in recommendation data that is the heterogeneity of prediction mechanism and covariate distribution and propose an algorithm that explores the heterogeneity through a bilevel clustering method. Furthermore, the uncovered heterogeneity is exploited for two purposes in recommendation scenarios which are prediction with multiple sub-models and supporting debias. Extensive experiments on real-world data validate the existence of heterogeneity in recommendation data and the effectiveness of exploring and exploiting data heterogeneity in recommendation.

As an intrinsic and fundamental property of big data, data heterogeneity exists in a variety of real-world applications, such as precision medicine, autonomous driving, financial applications, etc. For machine learning algorithms, the ignorance of data heterogeneity will greatly hurt the generalization performance and the algorithmic fairness, since the prediction mechanisms among different sub-populations are likely to differ from each other. In this work, we focus on the data heterogeneity that affects the prediction of machine learning models, and firstly propose the \emph{usable predictive heterogeneity}, which takes into account the model capacity and computational constraints. We prove that it can be reliably estimated from finite data with probably approximately correct (PAC) bounds. Additionally, we design a bi-level optimization algorithm to explore the usable predictive heterogeneity from data. Empirically, the explored heterogeneity provides insights for sub-population divisions in income prediction, crop yield prediction and image classification tasks, and leveraging such heterogeneity benefits the out-of-distribution generalization performance.

Machine learning algorithms with empirical risk minimization are vulnerable to distributional shifts due to the greedy adoption of all the correlations found in training data. Recently, there are robust learning methods aiming at this problem by minimizing the worst-case risk over an uncertainty set. However, they equally treat all covariates to form the uncertainty sets regardless of the stability of their correlations with the target, resulting in the overwhelmingly large set and low confidence of the learner. In this paper, we propose the Invariant Adversarial Learning (IAL) algorithm that leverages heterogeneous data sources to construct a more practical uncertainty set and conduct robustness optimization, where covariates are differentiated according to the stability of their correlations with the target. We theoretically show that our method is tractable for stochastic gradient-based optimization and provide the performance guarantees for our method.