Influence Functions for Scalable Data Attribution in Diffusion Models

B Mlodozeniec, R Eschenhagen, J Bae, A Immer, D Krueger, R Turner
ICLR, 2025
Overview

Abstract

Diffusion models have led to significant advancements in generative modelling. Yet their widespread adoption poses challenges regarding data attribution and interpretability. In this paper, we aim to help address such challenges in diffusion models by developing an influence functions framework.

Links