An official website of the United States government
During training, models can exploit spurious correlations as shortcuts, resulting in poor generalization performance when shortcuts do not persist. In this work, assuming access to a representation based on domain knowledge (i.e., known concepts) that is invariant to shortcuts, we aim to learn robust and accurate models from biased training data. In contrast to previous work, we do not rely solely on known concepts, but allow the model to also learn unknown concepts. We propose two approaches for mitigating shortcuts that incorporate domain knowledge, while accounting for potentially important yet unknown concepts. The first approach is two-staged. After fitting a model using known concepts, it accounts for the residual using unknown concepts. While flexible, we show that this approach is vulnerable when shortcuts are correlated with the unknown concepts. This limitation is addressed by our second approach that extends a recently proposed regularization penalty. Applied to two real-world datasets, we demonstrate that both approaches can successfully mitigate shortcut learning.
more »
« less
This content will become publicly available on December 11, 2025
Teaching invariance using priviledged mediation information
The performance of deep neural networks often deteriorates in out-of-distribution settings due to relying on easy-to-learn but unreliable spurious associations known as shortcuts. Recent work attempting to mitigate shortcut learning relies on a priori knowledge of what the shortcut is and requires a strict overlap assumption with respect to the shortcut and the labels. In this paper, we present a causally-motivated teacher-student framework that encourages invariance to all shortcuts by leveraging privileged mediation information. The Teaching Invariance using Privileged Mediation Information (TIPMI) framework distills knowledge from a counterfactually invariant teacher trained using privileged mediation information to a student predictor that uses non-privileged features. We analyze the theoretical properties of our proposed estimator, showing that TIPMI promotes invariance to multiple unknown shortcuts and has better finite-sample efficiency. We empirically verify our theoretical findings by showing that TIPMI outperforms several state-of-the-art methods on two vision datasets and one language dataset.
more »
« less
- Award ID(s):
- 2337529
- PAR ID:
- 10580212
- Publisher / Repository:
- Causal representation learning workshop at NeurIPS
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Deep neural networks are susceptible to shortcut learning, using simple features to achieve low training loss without discovering essential semantic structure. Contrary to prior belief, we show that generative models alone are not sufficient to prevent shortcut learning, despite an incentive to recover a more comprehensive representation of the data than discriminative approaches. However, we observe that shortcuts are preferentially encoded with minimal information, a fact that generative models can exploit to mitigate shortcut learning. In particular, we propose Chroma-VAE, a two-pronged approach where a VAE classifier is initially trained to isolate the shortcut in a small latent subspace, allowing a secondary classifier to be trained on the complementary, shortcut-free latent subspace. In addition to demonstrating the efficacy of Chroma-VAE on benchmark and real-world shortcut learning tasks, our work highlights the potential for manipulating the latent space of generative classifiers to isolate or interpret specific correlations.more » « less
-
For predictive models to provide reliable guidance in decision making processes, they are often required to be accurate and robust to distribution shifts. Shortcut learning–where a model relies on spurious correlations or shortcuts to predict the target label–undermines the robustness property, leading to models with poor out-of-distribution accuracy despite good in-distribution performance. Existing work on shortcut learning either assumes that the set of possible shortcuts is known a priori or is discoverable using interpretability methods such as saliency maps, which might not always be true. Instead, we propose a two step approach to (1) efficiently identify relevant shortcuts, and (2) leverage the identified shortcuts to build models that are robust to distribution shifts. Our approach relies on having access to a (possibly) high dimensional set of auxiliary labels at training time, some of which correspond to possible shortcuts. We show both theoretically and empirically that our approach is able to identify a sufficient set of shortcuts leading to more efficient predictors in finite samples.more » « less
-
Computer-supported collaborative learning (CSCL) is effective in improving students’ learning outcomes, yet CSCL research is rarely translated to classroom practice. To identify key CSCL research topics for K-12 STEM practice, we conducted a modified Delphi method study with a panel of practitioners and researchers. We relied on a knowledge mobilization framework to draw on expertise from both researchers, who produce new knowledge, and practitioners, who combine it with their pedagogical wisdom and use it in classrooms. We used the Delphi method because of its potential to address the power imbalances among panelists and modified it to facilitate knowledge mediation between knowledge production and use. The panelists identified seven key CSCL topics for translation from research into practice: Classroom discourse; Diversity, equity, and inclusion; Teacher preparation and professional development; Socially shared regulation of learning; Argumentation; Classroom orchestration and scripts; and Student and teacher identities. We also investigated panelists’ ideas on effective practitioner-researcher partnerships to inform the next stage of our project, where researchers and practitioners will jointly translate research from selected topics into practical guidance. We discuss our findings and the affordances and limitations of the Delphi method in knowledge mediation.more » « less
-
Policy distillation, which transfers a teacher policy to a student policy has achieved great success in challenging tasks of deep reinforcement learning. This teacher-student framework requires a well-trained teacher model which is computationally expensive. Moreover, the performance of the student model could be limited by the teacher model if the teacher model is not optimal. In the light of collaborative learning, we study the feasibility of involving joint intellectual efforts from diverse perspectives of student models. In this work, we introduce dual policy distillation (DPD), a student-student framework in which two learners operate on the same environment to explore different perspectives of the environment and extract knowledge from each other to enhance their learning. The key challenge in developing this dual learning framework is to identify the beneficial knowledge from the peer learner for contemporary learning-based reinforcement learning algorithms, since it is unclear whether the knowledge distilled from an imperfect and noisy peer learner would be helpful. To address the challenge, we theoretically justify that distilling knowledge from a peer learner will lead to policy improvement and propose a disadvantageous distillation strategy based on the theoretical results. The conducted experiments on several continuous control tasks show that the proposed framework achieves superior performance with a learning-based agent and function approximation without the use of expensive teacher models.more » « less
