DualXDA: Towards Sparse, Efficient and Explainable Data Attribution in Large AI Models
This addresses the need for scalable and interpretable AI explanations, particularly for large models, though it appears incremental by building on existing DA and feature attribution paradigms.
The paper tackles the problem of high computational costs and low sparsity in Data Attribution (DA) methods for explaining AI models by introducing DualXDA, which achieves up to 4,100,000× faster explanation times and improves attribution quality.
Deep learning models achieve remarkable performance, yet their decision-making processes often remain opaque. In response, the field of eXplainable Artificial Intelligence (XAI) has grown significantly over the last decade, primarily focusing on feature attribution methods. Complementing this perspective, Data Attribution (DA) has emerged as a promising paradigm that shifts the focus from features to data provenance. However, existing DA approaches suffer from prohibitively high computational costs and memory demands. Additionally, current attribution methods exhibit low sparsity, hindering the discovery of decisive patterns in the data. We introduce DualXDA, a framework for sparse, efficient and explainable DA, comprised of two interlinked approaches for Dual Data Attribution (DualDA) and eXplainable Data Attribution (XDA): With DualDA, we propose efficient and effective DA, leveraging Support Vector Machine theory to provide fast and naturally sparse data attributions for AI predictions. We demonstrate that DualDA achieves high attribution quality, excels at solving a series of evaluated downstream tasks, while at the same time improving explanation time by a factor of up to 4,100,000$\times$ compared to the original Influence Functions method, and up to 11,000$\times$ compared to the method's most efficient approximation from literature. We further introduce XDA, a method for enhancing Data Attribution with capabilities from feature attribution methods to explain why training samples are relevant for the prediction of a test sample in terms of impactful features. Taken together, our contributions in DualXDA ultimately point towards a future of eXplainable AI applied at unprecedented scale, enabling transparent, efficient and novel analysis of even the largest neural architectures fostering a new generation of accountable AI systems. Code at https://github.com/gumityolcu/DualXDA.