Achieving Data Efficient Neural Networks with Hybrid Concept-based Models
This work addresses data efficiency for machine learning practitioners, but it is incremental as it builds on existing concept-based approaches.
The paper tackles the problem of data efficiency in neural networks by introducing hybrid concept-based models that use both class labels and additional concept information, showing they outperform standard and previous concept-based models in accuracy, especially with sparse data, and also demonstrates adversarial concept attacks that challenge the interpretability of such models.
Most datasets used for supervised machine learning consist of a single label per data point. However, in cases where more information than just the class label is available, would it be possible to train models more efficiently? We introduce two novel model architectures, which we call hybrid concept-based models, that train using both class labels and additional information in the dataset referred to as concepts. In order to thoroughly assess their performance, we introduce ConceptShapes, an open and flexible class of datasets with concept labels. We show that the hybrid concept-based models outperform standard computer vision models and previously proposed concept-based models with respect to accuracy, especially in sparse data settings. We also introduce an algorithm for performing adversarial concept attacks, where an image is perturbed in a way that does not change a concept-based model's concept predictions, but changes the class prediction. The existence of such adversarial examples raises questions about the interpretable qualities promised by concept-based models.