Harmonizing Feature Attributions Across Deep Learning Architectures: Enhancing Interpretability and Consistency
This work addresses the need for reliable interpretability in machine learning for real-world deployment, though it appears incremental as it builds on existing feature attribution methods.
This study tackled the problem of inconsistent feature attributions across different deep learning architectures like CNNs and vision transformers, aiming to harmonize them to enhance interpretability and consistency, with results suggesting potential improvements in trust for machine learning applications.
Ensuring the trustworthiness and interpretability of machine learning models is critical to their deployment in real-world applications. Feature attribution methods have gained significant attention, which provide local explanations of model predictions by attributing importance to individual input features. This study examines the generalization of feature attributions across various deep learning architectures, such as convolutional neural networks (CNNs) and vision transformers. We aim to assess the feasibility of utilizing a feature attribution method as a future detector and examine how these features can be harmonized across multiple models employing distinct architectures but trained on the same data distribution. By exploring this harmonization, we aim to develop a more coherent and optimistic understanding of feature attributions, enhancing the consistency of local explanations across diverse deep-learning models. Our findings highlight the potential for harmonized feature attribution methods to improve interpretability and foster trust in machine learning applications, regardless of the underlying architecture.