Mixed Materials
Distilling Model Failures as Directions in Latent Space
| Title: | Distilling Model Failures as Directions in Latent Space |
|---|---|
| Authors: | Jain, Saachi, Lawrence, Hannah, Moitra, Ankur, Madry, Aleksander |
| Publisher Information: | 2022-06-29 2022-12-02 |
| Document Type: | Mixed materials |
| Abstract: | Existing methods for isolating hard subpopulations and spurious correlations in datasets often require human intervention. This can make these methods labor-intensive and dataset-specific. To address these shortcomings, we present a scalable method for automatically distilling a model's failure modes. Specifically, we harness linear classifiers to identify consistent error patterns, and, in turn, induce a natural representation of these failure modes as directions within the feature space. We demonstrate that this framework allows us to discover and automatically caption challenging subpopulations within the training dataset. Moreover, by combining our framework with off-the-shelf diffusion models, we can generate images that are especially challenging for the analyzed model, and thus can be used to perform synthetic data augmentation that helps remedy the model's failure modes. Code available at https://github.com/MadryLab/failure-directions |
| Index Terms: | Machine Learning, text |
| URL: | |
| Availability: | Open access content. Open access content |
| Other Numbers: | COO oai:arXiv.org:2206.14754 1381550552 |
| Contributing Source: | CORNELL UNIV From OAIster®, provided by the OCLC Cooperative. |
| Accession Number: | edsoai.on1381550552 |
| Database: | OAIster |
| Description not available. |