Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation

by   Yanrui Du, et al.

Many recent works indicate that the deep neural networks tend to take dataset biases as shortcuts to make decision, rather than understand the tasks, which results in failures on the real-world applications. In this work, we focus on the spurious correlation between feature and label, which derive from the biased data distribution in the training data, and analyze it concretely. In particular, we define the word highly co-occurring with a specific label as biased word, and the example containing biased word as biased example. Our analysis reveals that the biased examples with spurious correlations are easier for models to learn, and when predicting, the biased words make significantly higher contributions to models' predictions than other words, and the models tend to assign the labels over-relying on the spurious correlation between words and labels. To mitigate the model's over-reliance on the shortcut, we propose a training strategy Less-Learn-Shortcut (LLS): we quantify the biased degree of the biased examples, and down-weight them with the biased degree. Experimental results on QM and NLI tasks show that the models improve the performances both on in-domain and adversarial data (1.57 HANS) with our LLS.


SelecMix: Debiased Learning by Contradicting-pair Sampling

Neural networks trained with ERM (empirical risk minimization) sometimes...

An adversarial feature learning strategy for debiasing neural networks

Simplicity bias is the concerning tendency of deep networks to over-depe...

Learning from Failure: Training Debiased Classifier from Biased Classifier

Neural networks often learn to make predictions that overly rely on spur...

How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning

Shortcut learning, or `Clever Hans effect` refers to situations where a ...

From Hope to Safety: Unlearning Biases of Deep Models by Enforcing the Right Reasons in Latent Space

Deep Neural Networks are prone to learning spurious correlations embedde...

Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering

Extractive question answering (QA) models tend to exploit spurious corre...

Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities

Several proposals have been put forward in recent years for improving ou...

Please sign up or login with your details

Forgot password? Click here to reset