Sub-population shift is a specific type of domain shift that highlights changes in data distribution within specific sub-groups or populations between training and testing. Sub-population shift accounts for a significant source of algorithmic bias and calls for distributional robustness. Recent studies found inherent distributional robustness in multi-modality foundation models, such as the vision-language model CLIP, yet this robustness is vulnerable through parameter fine-tuning. In this paper, we propose leveraging the connection of robustness among different modalities and reshaping the distributional robustness of one modality with another. Specifically, in the context of the distributional robustness of CLIP, we propose to leverage natural language inputs to debias the image feature representations, to improve worst-case performance on sub-populations. Our extensive empirical studies show that image representations debiased by natural language can achieve significant performance improvement and reduction of performance instability under sub-population shifts.

When training and evaluating machine learning models on a large number of tasks, it is important to not only look at average task accuracy--which may be biased by easy or redundant tasks--but also worst-case accuracy (i.e. the performance on the task with the lowest accuracy). In this work, we show how to use techniques from the distributionally robust optimization (DRO) literature to improve worst-case performance in multitask learning. We highlight several failure cases of DRO when applied off-the-shelf and present an improved method, Lookahead-DRO (L-DRO), which mitigates these issues. The core idea of L-DRO is to anticipate the interaction between tasks during training in order to choose a dynamic re-weighting of the various task losses, which will (i) lead to minimal worst-case loss and (ii) train on as many tasks as possible. After demonstrating the efficacy of L-DRO on a small controlled synthetic setting, we evaluate it on two realistic benchmarks: a multitask version of the CIFAR-100 image classification dataset and a large-scale multilingual language modeling experiment. Our empirical results show that L-DRO achieves a better trade-off between average and worst-case accuracy with little computational overhead compared to several strong baselines. Multitask learning--the process by which a single model is trained to perform a variety of different tasks--has become a subject of increasing interest with many successful applications in a variety of domains (Ruder, 2017; Yu et al., 2020; Wang et al., 2021).