Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution
This addresses the problem of scalability for researchers and practitioners in explainable ML by accelerating key tasks, though it is incremental as it builds on amortization techniques.
The paper tackles the computational inefficiency of explainable ML tasks like feature attribution and data valuation by proposing to train amortized models with noisy labels, which is inexpensive and effective. The approach tolerates high noise levels and achieves significant speedups, often an order of magnitude faster than existing methods.
Many tasks in explainable machine learning, such as data valuation and feature attribution, perform expensive computation for each data point and are intractable for large datasets. These methods require efficient approximations, and although amortizing the process by learning a network to directly predict the desired output is a promising solution, training such models with exact labels is often infeasible. We therefore explore training amortized models with noisy labels, and we find that this is inexpensive and surprisingly effective. Through theoretical analysis of the label noise and experiments with various models and datasets, we show that this approach tolerates high noise levels and significantly accelerates several feature attribution and data valuation methods, often yielding an order of magnitude speedup over existing approaches.