More Like this

1. Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations

   Kirichenko, Polina; Izmailov, Pavel; Gordon Wilson, Andrew (June 2023, ICLR 2023)

   Neural network classifiers can largely rely on simple spurious features, such as backgrounds, to make predictions. However, even in these cases, we show that they still often learn core features associated with the desired attributes of the data, contrary to recent findings. Inspired by this insight, we demonstrate that simple last layer retraining can match or outperform state-of-the-art approaches on spurious correlation benchmarks, but with profoundly lower complexity and computational expenses. Moreover, we show that last layer retraining on large ImageNet-trained models can also significantly reduce reliance on background and texture information, improving robustness to covariate shift, after only minutes of training on a single GPU. 

   more » « less
2. Label Noise Robustness for Domain-Agnostic Fair Corrections via Nearest Neighbors Label Spreading

   Stromberg, Nathan; Ayyagari, Rohan; Koyejo, Sanmi; Nock, Richard; Sankar, Lalitha (December 2024, Curran Associates, Inc. Advances in Neural Information Processing Systems)

   Globerson, A; Mackey, L; Belgrave, D; Fan, A; Paquet, U; Tomczak, J; Zhang, C (Ed.)

   Last-layer retraining methods have emerged as an efficient framework for correcting existing base models. Within this framework, several methods have been proposed to deal with correcting models for subgroup fairness with and without group membership information. Importantly, prior work has demonstrated that many methods are susceptible to noisy labels. To this end, we propose a drop-in correction for label noise in last-layer retraining, and demonstrate that it achieves state-ofthe-art worst-group accuracy for a broad range of symmetric label noise and across a wide variety of datasets exhibiting spurious correlations. Our proposed approach uses label spreading on a latent nearest neighbors graph and has minimal computational overhead compared to existing methods. 

   more » « less
3. On Feature Learning in the Presence of Spurious Correlations

   Izmailov, Pavel; Kirichenko, Polina; Gruver, Nate; Wilson, Andrew Gordon (October 2022, NeurIPS)

   Deep classifiers are known to rely on spurious features — 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 the foregrounds. In this paper we evaluate the amount of information about the core (non-spurious) features that can be decoded from the representations learned by standard empirical risk minimization (ERM) and specialized group robustness training. Following recent work on Deep Feature Reweighting (DFR), we evaluate the feature representations by re-training the last layer of the model on a held-out set where the spurious correlation is broken. On multiple vision and NLP problems, we show that the features learned by simple ERM are highly competitive with the features learned by specialized group robustness methods targeted at reducing the effect of spurious correlations. Moreover, we show that the quality of learned feature representations is greatly affected by the design decisions beyond the training method, such as the model architecture and pre-training strategy. On the other hand, we find that strong regularization is not necessary for learning high-quality feature representations. Finally, using insights from our analysis, we significantly improve upon the best results reported in the literature on the popular Waterbirds, CelebA hair color prediction and WILDS-FMOW problems, achieving 97\%, 92\% and 50\% worst-group accuracies, respectively. 

   more » « less
4. Simple and Fast Group Robustness by Automatic Feature Reweighting

   Qiu, Shikai; Potapczynski, Andres; Izmailov, Pavel; Gordon Wilson, Andrew (June 2023, ICML 2023)

   A major challenge to out-of-distribution generalization is reliance on spurious features -- patterns that are predictive of the class label in the training data distribution, but not causally related to the target. Standard methods for reducing the reliance on spurious features typically assume that we know what the spurious feature is, which is rarely true in the real world. Methods that attempt to alleviate this limitation are complex, hard to tune, and lead to a significant computational overhead compared to standard training. In this paper, we propose Automatic Feature Reweighting (AFR), an extremely simple and fast method for updating the model to reduce the reliance on spurious features. AFR retrains the last layer of a standard ERM-trained base model with a weighted loss that emphasizes the examples where the ERM model predicts poorly, automatically upweighting the minority group without group labels. With this simple procedure, we improve upon the best reported results among competing methods trained without spurious attributes on several vision and natural language classification benchmarks, using only a fraction of their compute. 

   more » « less
5. Robustness to Subpopulation Shift with Domain Label Noise via Regularized Annotation of Domains

   Stromberg, Nathan; Ayyagari, Rohan; Welfert, Monica; Koyejo, Sanmi; Nock, Richard; Sankar, Lalitha (December 2024, Transactions on machine learning research)

   NA (Ed.)

   Existing methods for last layer retraining that aim to optimize worst-group accuracy (WGA) rely heavily on well-annotated groups in the training data. We show, both in theory and practice, that annotation-based data augmentations using either downsampling or upweighting for WGA are susceptible to domain annotation noise. The WGA gap is exacerbated in highnoise regimes for models trained with vanilla empirical risk minimization (ERM). To this end, we introduce Regularized Annotation of Domains (RAD) to train robust last layer classifiers without needing explicit domain annotations. Our results show that RAD is competitive with other recently proposed domain annotation-free techniques. Most importantly, RAD outperforms state-of-the-art annotation-reliant methods even with only 5% noise in the training data for several publicly available datasets. 

   more » « less