Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization
- URL: http://arxiv.org/abs/2305.12123v1
- Date: Sat, 20 May 2023 07:02:27 GMT
- Title: Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization
- Authors: Ting Wu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
- Abstract summary: Group distributionally robust optimization (group DRO) can minimize the worst-case loss over pre-defined groups.
We reformulate the group DRO framework by proposing Q-Diversity.
Characterized by an interactive training mode, Q-Diversity relaxes the group identification from annotation into direct parameterization.
- Score: 61.39201891894024
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Models trained with empirical risk minimization (ERM) are revealed to easily
rely on spurious correlations, resulting in poor generalization. Group
distributionally robust optimization (group DRO) can alleviate this problem by
minimizing the worst-case loss over pre-defined groups. While promising, in
practice factors like expensive annotations and privacy preclude the
availability of group labels. More crucially, when taking a closer look at the
failure modes of out-of-distribution generalization, the typical procedure of
reweighting in group DRO loses efficiency. Hinged on the limitations, in this
work, we reformulate the group DRO framework by proposing Q-Diversity.
Characterized by an interactive training mode, Q-Diversity relaxes the group
identification from annotation into direct parameterization. Furthermore, a
novel mixing strategy across groups is presented to diversify the
under-represented groups. In a series of experiments on both synthetic and
real-world text classification tasks, results demonstrate that Q-Diversity can
consistently improve worst-case accuracy under different distributional shifts,
outperforming state-of-the-art alternatives.
Related papers
- Trained Models Tell Us How to Make Them Robust to Spurious Correlation without Group Annotation [3.894771553698554]
Empirical Risk Minimization (ERM) models tend to rely on attributes that have high spurious correlation with the target.
This can degrade the performance on underrepresented (or'minority') groups that lack these attributes.
We propose Environment-based Validation and Loss-based Sampling (EVaLS) to enhance robustness to spurious correlation.
arXiv Detail & Related papers (2024-10-07T08:17:44Z) - Ranking & Reweighting Improves Group Distributional Robustness [14.021069321266516]
We propose a ranking-based training method called Discounted Rank Upweighting (DRU) to learn models that exhibit strong OOD performance on the test data.
Results on several synthetic and real-world datasets highlight the superior ability of our group-ranking-based (akin to soft-minimax) approach in selecting and learning models that are robust to group distributional shifts.
arXiv Detail & Related papers (2023-05-09T20:37:16Z) - AGRO: Adversarial Discovery of Error-prone groups for Robust
Optimization [109.91265884632239]
Group distributionally robust optimization (G-DRO) can minimize the worst-case loss over a set of pre-defined groups over training data.
We propose AGRO -- Adversarial Group discovery for Distributionally Robust Optimization.
AGRO results in 8% higher model performance on average on known worst-groups, compared to prior group discovery approaches.
arXiv Detail & Related papers (2022-12-02T00:57:03Z) - Take One Gram of Neural Features, Get Enhanced Group Robustness [23.541213868620837]
Predictive performance of machine learning models trained with empirical risk minimization can degrade considerably under distribution shifts.
We propose to partition the training dataset into groups based on Gram matrices of features extracted by an identification'' model.
Our approach not only improves group robustness over ERM but also outperforms all recent baselines.
arXiv Detail & Related papers (2022-08-26T12:34:55Z) - Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios.
We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
arXiv Detail & Related papers (2022-04-13T12:43:12Z) - Focus on the Common Good: Group Distributional Robustness Follows [47.62596240492509]
This paper proposes a new and simple algorithm that explicitly encourages learning of features that are shared across various groups.
While Group-DRO focuses on groups with worst regularized loss, focusing instead, on groups that enable better performance even on other groups, could lead to learning of shared/common features.
arXiv Detail & Related papers (2021-10-06T09:47:41Z) - Just Train Twice: Improving Group Robustness without Training Group
Information [101.84574184298006]
Standard training via empirical risk minimization can produce models that achieve high accuracy on average but low accuracy on certain groups.
Prior approaches that achieve high worst-group accuracy, like group distributionally robust optimization (group DRO) require expensive group annotations for each training point.
We propose a simple two-stage approach, JTT, that first trains a standard ERM model for several epochs, and then trains a second model that upweights the training examples that the first model misclassified.
arXiv Detail & Related papers (2021-07-19T17:52:32Z) - Examining and Combating Spurious Features under Distribution Shift [94.31956965507085]
We define and analyze robust and spurious representations using the information-theoretic concept of minimal sufficient statistics.
We prove that even when there is only bias of the input distribution, models can still pick up spurious features from their training data.
Inspired by our analysis, we demonstrate that group DRO can fail when groups do not directly account for various spurious correlations.
arXiv Detail & Related papers (2021-06-14T05:39:09Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.