Deep Neural Networks inherit spurious correlations embedded in training data and hence may fail to predict desired labels on unseen domains (or environments), which have different distributions from the domain to provide training data. Invariance Learning (IL) has been developed recently to overcome this shortcoming; using training data in many domains, IL estimates such a predictor that is invariant to a change of domain. However, the requirement of training data in multiple domains is a strong restriction of using IL, since it demands expensive annotation. We propose a novel IL framework to overcome this problem. Assuming the availability of data from multiple domains for a higher level of classification task, for which the labeling cost is lower, we estimate an invariant predictor for the target classification task with training data gathered in a single domain. Additionally, we propose two cross-validation methods for selecting hyperparameters of invariance regularization, which has not been addressed properly in existing IL methods. The effectiveness of the proposed framework, including the cross-validation, is demonstrated empirically. Theoretical analysis reveals that our framework can estimate the desirable invariant predictor with a hyperparameter fixed correctly, and that such a preferable hyperparameter is chosen by the proposed CV methods under some conditions.

Models are expected to engage in invariance learning, which involves distinguishing the core relations that remain consistent across varying environments to ensure the predictions are safe, robust and fair. While existing works consider specific algorithms to realize invariance learning, we show that model has the potential to learn invariance through standard training procedures. In other words, this paper studies the implicit bias of Stochastic Gradient Descent (SGD) over heterogeneous data and shows that the implicit bias drives the model learning towards an invariant solution. We call the phenomenon the implicit invariance learning. Specifically, we theoretically investigate the multi-environment low-rank matrix sensing problem where in each environment, the signal comprises (i) a lower-rank invariant part shared across all environments; and (ii) a significantly varying environment-dependent spurious component. The key insight is, through simply employing the large step size large-batch SGD sequentially in each environment without any explicit regularization, the oscillation caused by heterogeneity can provably prevent model learning spurious signals. The model reaches the invariant solution after certain iterations. In contrast, model learned using pooled SGD over all data would simultaneously learn both the invariant and spurious signals. Overall, we unveil another implicit bias that is a result of the symbiosis between the heterogeneity of data and modern algorithms, which is, to the best of our knowledge, first in the literature.

Data augmentation is commonly applied to improve performance of deep learning by enforcing the knowledge that certain transformations on the input preserve the output. Currently, the data augmentation parameters are chosen by human effort and costly cross-validation, which makes it cumbersome to apply to new datasets. We develop a convenient gradient-based method for selecting the data augmentation without validation data during training of a deep neural network. Our approach relies on phrasing data augmentation as an invariance in the prior distribution on the functions of a neural network, which allows us to learn it using Bayesian model selection. This has been shown to work in Gaussian processes, but not yet for deep neural networks. We propose a differentiable Kronecker-factored Laplace approximation to the marginal likelihood as our objective, which can be optimised without human supervision or validation data. We show that our method can successfully recover invariances present in the data, and that this improves generalisation and data efficiency on image datasets.

Deep Neural Networks inherit biased correlations embedded in training data and hence may fail to predict desired labels on unseen domains (or environments), which have different distributions from the domain to provide training data. Invariance Learning (IL) has been developed recently to overcome this shortcoming; using training data in many domains, IL estimates such a predictor that is invariant to a change of domain. However, the requirement of training data in multiple domains is a strong restriction of using IL, since it demands expensive annotation. We propose a novel IL framework to overcome this problem. Assuming the availability of data from multiple domains for a classification task at a higher level, for which the labeling cost is lower, we estimate an invariant predictor for the target classification task with training data gathered in a single domain. Additionally, we propose two cross-validation methods for selecting hyperparameters of invariance regularization, which has not been addressed properly in existing IL methods. The effectiveness of the proposed framework, including the cross-validation, is demonstrated empirically. Theoretical analysis reveals that our framework can estimate the desirable invariant predictor with a hyperparameter fixed correctly, and that such a preferable hyperparameter is chosen by the proposed CV methods under some conditions.

Models are expected to engage in invariance learning, which involves distinguishing the core relations that remain consistent across varying environments to ensure the predictions are safe, robust and fair. While existing works consider specific algorithms to realize invariance learning, we show that model has the potential to learn invariance through standard training procedures. In other words, this paper studies the implicit bias of Stochastic Gradient Descent (SGD) over heterogeneous data and shows that the implicit bias drives the model learning towards an invariant solution. We call the phenomenon the implicit invariance learning. Specifically, we theoretically investigate the multi-environment low-rank matrix sensing problem where in each environment, the signal comprises (i) a lower-rank invariant part shared across all environments; and (ii) a significantly varying environment-dependent spurious component. The key insight is, through simply employing the large step size large-batch SGD sequentially in each environment without any explicit regularization, the oscillation caused by heterogeneity can provably prevent model learning spurious signals.

Deep Neural Networks inherit spurious correlations embedded in training data and hence may fail to predict desired labels on unseen domains (or environments), which have different distributions from the domain to provide training data. Invariance Learning (IL) has been developed recently to overcome this shortcoming; using training data in many domains, IL estimates such a predictor that is invariant to a change of domain. However, the requirement of training data in multiple domains is a strong restriction of using IL, since it demands expensive annotation. We propose a novel IL framework to overcome this problem. Assuming the availability of data from multiple domains for a higher level of classification task, for which the labeling cost is lower, we estimate an invariant predictor for the target classification task with training data gathered in a single domain.

Data augmentation is commonly applied to improve performance of deep learning by enforcing the knowledge that certain transformations on the input preserve the output. Currently, the data augmentation parameters are chosen by human effort and costly cross-validation, which makes it cumbersome to apply to new datasets. We develop a convenient gradient-based method for selecting the data augmentation without validation data during training of a deep neural network. Our approach relies on phrasing data augmentation as an invariance in the prior distribution on the functions of a neural network, which allows us to learn it using Bayesian model selection. This has been shown to work in Gaussian processes, but not yet for deep neural networks.

Contrastive learning has recently shown immense potential in unsupervised visual representation learning. Existing studies in this track mainly focus on intra-image invariance learning. The learning typically uses rich intra-image transformations to construct positive pairs and then maximizes agreement using a contrastive loss. The merits of inter-image invariance, conversely, remain much less explored. One major obstacle to exploit inter-image invariance is that it is unclear how to reliably construct inter-image positive pairs, and further derive effective supervision from them since no pair annotations are available. In this work, we present a comprehensive empirical study to better understand the role of inter-image invariance learning from three main constituting components: pseudo-label maintenance, sampling strategy, and decision boundary design. To facilitate the study, we introduce a unified and generic framework that supports the integration of unsupervised intra- and inter-image invariance learning. Through carefully-designed comparisons and analysis, multiple valuable observations are revealed: 1) online labels converge faster and perform better than offline labels; 2) semi-hard negative samples are more reliable and unbiased than hard negative samples; 3) a less stringent decision boundary is more favorable for inter-image invariance learning. With all the obtained recipes, our final model, namely InterCLR, shows consistent improvements over state-of-the-art intra-image invariance learning methods on multiple standard benchmarks. We hope this work will provide useful experience for devising effective unsupervised inter-image invariance learning. Code: https://github.com/open-mmlab/mmselfsup.

Deep Neural Networks inherit spurious correlations embedded in training data and hence may fail to predict desired labels on unseen domains (or environments), which have different distributions from the domain used in training. Invariance Learning (IL) has been developed recently to overcome this shortcoming; using training data in many domains, IL estimates such a predictor that is invariant to a change of domain. However, the requirement of training data in multiple domains is a strong restriction of IL, since it often needs high annotation cost. We propose a novel IL framework to overcome this problem. Assuming the availability of data from multiple domains for a higher level of classification task, for which the labeling cost is low, we estimate an invariant predictor for the target classification task with training data in a single domain. Additionally, we propose two cross-validation methods for selecting hyperparameters of invariance regularization to solve the issue of hyperparameter selection, which has not been handled properly in existing IL methods. The effectiveness of the proposed framework, including the cross-validation, is demonstrated empirically, and the correctness of the hyperparameter selection is proved under some conditions.