Better Training Data Attribution via Better Inverse Hessian-Vector Products

Andrew Wang, Elisa Nguyen, Runshi Yang, Juhan Bae, Sheila A. McIlraith, Roger Baker Grosse

Keywords: Influence Functions, Interpretability

TL;DR: We apply the EKFAC-preconditioner on Neumann series iterations to arrive at an unbiased iHVP approximation for TDA that improves influence function and unrolled differentiation performance.

Abstract: Training data attribution (TDA) provides insights into which training data is responsible for a learned model behavior. Gradient-based TDA methods such as influence functions and unrolled differentiation both involve a computation that resembles an inverse Hessian-vector product (iHVP), which is difficult to approximate efficiently. We introduce an algorithm (ASTRA) which uses the EKFAC-preconditioner on Neumann series iterations to arrive at an accurate iHVP approximation for TDA. ASTRA is easy to tune, requires fewer iterations than Neumann series iterations, and is more accurate than EKFAC-based approximations. Using ASTRA, we show that improving the accuracy of the iHVP approximation can significantly improve TDA performance.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 10946