# Intervening on early readouts for mitigating spurious features and simplicity bias

DevFeed: [Intervening on early readouts for mitigating spurious features and simplicity bias](<https://devfeed.tech/articles/intervening-on-early-readouts-for-mitigating-spurious-features-and-simplicity-bias-28549.md>)

Original publisher: [Read original article](<http://blog.research.google/2024/02/intervening-on-early-readouts-for.html>)

Author: Google AI (noreply@blogger.com)

Published: 2024-02-02T17:49:00Z

Content type: article

Language: en

Sources: [Google Research](<https://devfeed.tech/sources/google-research.md>)

Topics: [AI Research](<https://devfeed.tech/topics/ai-research.md>), [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [responsible-ai](<https://devfeed.tech/topics/responsible-ai.md>), [generalization in machine learning](<https://devfeed.tech/topics/generalization-in-machine-learning.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>), [Training AI Models](<https://devfeed.tech/topics/training-ai-models.md>)

Tags: [bias](<https://devfeed.tech/tags/bias.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [icml](<https://devfeed.tech/tags/icml.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [ml-fairness](<https://devfeed.tech/tags/ml-fairness.md>), [research](<https://devfeed.tech/tags/research.md>), [responsible-ai](<https://devfeed.tech/tags/responsible-ai.md>), [supervised-learning](<https://devfeed.tech/tags/supervised-learning.md>), [training](<https://devfeed.tech/tags/training.md>)

## AI overview

Google Research describes methods for detecting and reducing spurious features and simplicity bias in deep learning models. Early readouts expose confidently wrong predictions associated with spurious features, while feature forgetting helps models identify more predictive features and generalize to unseen domains.

## Source excerpt

Posted by Rishabh Tiwari, Pre-doctoral Researcher, and Pradeep Shenoy, Research Scientist, Google Research Machine learning models in the real world are often trained on limited data that may contain unintended statistical biases. For example, in the CELEBA celebrity image dataset, a disproportionate number of female celebrities have blond hair, leading to classifiers incorrectly predicting "blond" as the hair color for most female faces -- here, gender is a spurious feature for predicting hair color. Such unfair biases could have significant consequences in critical applications such as medical diagnosis. Surprisingly, recent work has also discovered an inherent tendency of deep networks to amplify such statistical biases, through the so-called simplicity bias of deep learning. This bias is the tendency of deep networks to identify weakly predictive features early in the training, and continue to anchor on these features, failing to identify more complex and potentially more accurate features. With the above in mind, we propose simple and effective fixes to this dual challenge of spurious features and simplicity bias by applying early readouts and feature forgetting. First, in "Using Early Readouts to Mediate Featural Bias in Distillation", we show that making predictions from early layers of a deep network (referred to as "early readouts") can automatically signal issues with the quality of the learned representations. In particular, these predictions are more often wrong, and more confidently wrong, when the network is relying on spurious features. We use this erroneous confidence to improve outcomes in model distillation, a setting where a larger "teacher" model guides the training of a smaller "student" model. Then in "Overcoming Simplicity Bias in Deep Networks using a Feature Sieve", we intervene directly on these indicator signals by making the network "forget" the problematic features and consequently look for better, more predictive features. This substanti