Let Samples Speak: Mitigating Spurious Correlation by Exploiting the Clusterness of Samples
By: Weiwei Li , Junzhuo Liu , Yuanyuan Ren and more
Potential Business Impact:
Fixes computer learning mistakes caused by bad data.
Deep learning models are known to often learn features that spuriously correlate with the class label during training but are irrelevant to the prediction task. Existing methods typically address this issue by annotating potential spurious attributes, or filtering spurious features based on some empirical assumptions (e.g., simplicity of bias). However, these methods may yield unsatisfactory performance due to the intricate and elusive nature of spurious correlations in real-world data. In this paper, we propose a data-oriented approach to mitigate the spurious correlation in deep learning models. We observe that samples that are influenced by spurious features tend to exhibit a dispersed distribution in the learned feature space. This allows us to identify the presence of spurious features. Subsequently, we obtain a bias-invariant representation by neutralizing the spurious features based on a simple grouping strategy. Then, we learn a feature transformation to eliminate the spurious features by aligning with this bias-invariant representation. Finally, we update the classifier by incorporating the learned feature transformation and obtain an unbiased model. By integrating the aforementioned identifying, neutralizing, eliminating and updating procedures, we build an effective pipeline for mitigating spurious correlation. Experiments on image and NLP debiasing benchmarks show an improvement in worst group accuracy of more than 20% compared to standard empirical risk minimization (ERM). Codes and checkpoints are available at https://github.com/davelee-uestc/nsf_debiasing .
Similar Papers
Severing Spurious Correlations with Data Pruning
Machine Learning (CS)
Cleans computer learning data to prevent mistakes.
Post-hoc Spurious Correlation Neutralization with Single-Weight Fictitious Class Unlearning
CV and Pattern Recognition
Fixes AI mistakes caused by fake clues.
Elastic Representation: Mitigating Spurious Correlations for Group Robustness
Machine Learning (CS)
Makes AI fair for everyone, not just most.