Mitigating Simplicity Bias in Deep Learning for Improved OOD
Generalization and Robustness
- URL: http://arxiv.org/abs/2310.06161v1
- Date: Mon, 9 Oct 2023 21:19:39 GMT
- Title: Mitigating Simplicity Bias in Deep Learning for Improved OOD
Generalization and Robustness
- Authors: Bhavya Vasudeva, Kameron Shahabi, Vatsal Sharan
- Abstract summary: We propose a framework that encourages the model to use a more diverse set of features to make predictions.
We first train a simple model, and then regularize the conditional mutual information with respect to it to obtain the final model.
We demonstrate the effectiveness of this framework in various problem settings and real-world applications.
- Score: 5.976013616522926
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Neural networks (NNs) are known to exhibit simplicity bias where they tend to
prefer learning 'simple' features over more 'complex' ones, even when the
latter may be more informative. Simplicity bias can lead to the model making
biased predictions which have poor out-of-distribution (OOD) generalization. To
address this, we propose a framework that encourages the model to use a more
diverse set of features to make predictions. We first train a simple model, and
then regularize the conditional mutual information with respect to it to obtain
the final model. We demonstrate the effectiveness of this framework in various
problem settings and real-world applications, showing that it effectively
addresses simplicity bias and leads to more features being used, enhances OOD
generalization, and improves subgroup robustness and fairness. We complement
these results with theoretical analyses of the effect of the regularization and
its OOD generalization properties.
Related papers
- Improving Network Interpretability via Explanation Consistency Evaluation [56.14036428778861]
We propose a framework that acquires more explainable activation heatmaps and simultaneously increase the model performance.
Specifically, our framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning.
Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations.
arXiv Detail & Related papers (2024-08-08T17:20:08Z) - Model Reprogramming Outperforms Fine-tuning on Out-of-distribution Data in Text-Image Encoders [56.47577824219207]
In this paper, we unveil the hidden costs associated with intrusive fine-tuning techniques.
We introduce a new model reprogramming approach for fine-tuning, which we name Reprogrammer.
Our empirical evidence reveals that Reprogrammer is less intrusive and yields superior downstream models.
arXiv Detail & Related papers (2024-03-16T04:19:48Z) - Towards Calibrated Robust Fine-Tuning of Vision-Language Models [97.19901765814431]
This work proposes a robust fine-tuning method that improves both OOD accuracy and confidence calibration simultaneously in vision language models.
We show that both OOD classification and OOD calibration errors have a shared upper bound consisting of two terms of ID data.
Based on this insight, we design a novel framework that conducts fine-tuning with a constrained multimodal contrastive loss enforcing a larger smallest singular value.
arXiv Detail & Related papers (2023-11-03T05:41:25Z) - Spurious Feature Diversification Improves Out-of-distribution Generalization [43.84284578270031]
Generalization to out-of-distribution (OOD) data is a critical challenge in machine learning.
We study WiSE-FT, a popular weight space ensemble method that interpolates between a pre-trained and a fine-tuned model.
We observe an unexpected FalseFalseTrue" phenomenon, in which WiSE-FT successfully corrects many cases where each individual model makes incorrect predictions.
arXiv Detail & Related papers (2023-09-29T13:29:22Z) - Sparsity-aware generalization theory for deep neural networks [12.525959293825318]
We present a new approach to analyzing generalization for deep feed-forward ReLU networks.
We show fundamental trade-offs between sparsity and generalization.
arXiv Detail & Related papers (2023-07-01T20:59:05Z) - Understanding and Improving Feature Learning for Out-of-Distribution
Generalization [41.06375309780553]
We propose Feature Augmented Training (FeAT) to enforce the model to learn richer features ready for OOD generalization.
FeAT iteratively augments the model to learn new features while retaining the already learned features.
Experiments show that FeAT effectively learns richer features thus boosting the performance of various OOD objectives.
arXiv Detail & Related papers (2023-04-22T05:57:00Z) - General Greedy De-bias Learning [163.65789778416172]
We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space.
GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
arXiv Detail & Related papers (2021-12-20T14:47:32Z) - Improved OOD Generalization via Adversarial Training and Pre-training [49.08683910076778]
In this paper, we theoretically show that a model robust to input perturbations generalizes well on OOD data.
Inspired by previous findings that adversarial training helps improve input-robustness, we show that adversarially trained models have converged excess risk on OOD data.
arXiv Detail & Related papers (2021-05-24T08:06:35Z) - Evading the Simplicity Bias: Training a Diverse Set of Models Discovers
Solutions with Superior OOD Generalization [93.8373619657239]
Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features.
This simplicity bias can explain their lack of robustness out of distribution (OOD)
We demonstrate that the simplicity bias can be mitigated and OOD generalization improved.
arXiv Detail & Related papers (2021-05-12T12:12:24Z)
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.