Removing Multiple Shortcuts through the Lens of Multi-task Learning
Primary Area: societal considerations including fairness, safety, privacy
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Debiasing, spurious correlation, multiple biases, shortcut learning
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We present a novel training algorithm mitigating multiple biases of training data based on a theory of multi-task learning, along with a new real-image multi-bias dataset to facilitate future research in this direction.
Abstract: We consider the problem of training an unbiased and accurate model using a biased dataset with multiple biases. This problem is challenging since the multiple biases cause multiple undesirable shortcuts during training, and even worse, mitigating one of them may exacerbate another. To address this challenge, we introduce a novel method connecting the problem to multi-task learning (MTL). Our method divides training data into several groups according to their effects on the model bias and defines each task of MTL as solving the target problem for each group. It in turn trains a single model for all the tasks with a weighted sum of task-wise losses as the training objective, while optimizing the weights as well as the model parameters. At the heart of our method lies the weight adjustment algorithm, which is rooted in a theory of multi-objective optimization and guarantees a Pareto-stationary solution. In addition, we also present a new real-image dataset with multiple biases, dubbed MultiCelebA, for evaluating debiased training methods under realistic and challenging scenarios. Our method achieved the state of the art on three datasets with multiple biases including MultiCelebA, and demonstrated superior performance on conventional single-bias datasets.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 1800
Loading