SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.02174 · 2023

Training Data Attribution for Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Diffusion models have become increasingly popular for synthesizing high-quality samples based on training datasets. However, given the oftentimes enormous sizes of the training datasets, it is difficult to assess how training data impact the samples produced by a trained diffusion model. The difficulty of relating diffusion model inputs and outputs poses significant challenges to model explainability and training data attribution. Here we propose a novel solution that reveals how training data influence the output of diffusion models through the use of ensembles. In our approach individual models in an encoded ensemble are trained on carefully engineered splits of the overall training data to permit the identification of influential training examples. The resulting model ensembles enable efficient ablation of training data influence, allowing us to assess the impact of training data on model outputs. We demonstrate the viability of these ensembles as generative models and the validity of our approach to assessing influence.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2306.02174")
get_code_for_paper("2306.02174")
have("2306.02174")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2306.02174.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2306.02174.svg)](https://syntology.ai/paper/2306.02174)

Connect an agent — have() is free.