Training Data Attribution for Diffusion Models
- URL: http://arxiv.org/abs/2306.02174v1
- Date: Sat, 3 Jun 2023 18:36:12 GMT
- Title: Training Data Attribution for Diffusion Models
- Authors: Zheng Dai and David K Gifford
- Abstract summary: 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.
- Score: 1.1733780065300188
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- Ablation Based Counterfactuals [7.481286710933861]
Ablation Based Counterfactuals (ABC) is a method of performing counterfactual analysis that relies on model ablation rather than model retraining.
We demonstrate how we can construct a model like this using an ensemble of diffusion models.
We then use this model to study the limits of training data attribution by enumerating full counterfactual landscapes.
arXiv Detail & Related papers (2024-06-12T06:22:51Z) - An Efficient Framework for Crediting Data Contributors of Diffusion Models [13.761241561734547]
We introduce a method to efficiently retrain and rerun inference for Shapley value estimation.
We evaluate the utility of our method with three use cases: (i) image quality for a DDPM trained on a CIFAR dataset, (ii) demographic diversity for an LDM trained on CelebA-HQ, and (iii) aesthetic quality for a Stable Diffusion model LoRA-finetuned on Post-Impressionist artworks.
arXiv Detail & Related papers (2024-06-09T17:42:09Z) - Distilled Datamodel with Reverse Gradient Matching [74.75248610868685]
We introduce an efficient framework for assessing data impact, comprising offline training and online evaluation stages.
Our proposed method achieves comparable model behavior evaluation while significantly speeding up the process compared to the direct retraining method.
arXiv Detail & Related papers (2024-04-22T09:16:14Z) - Towards Theoretical Understandings of Self-Consuming Generative Models [56.84592466204185]
This paper tackles the emerging challenge of training generative models within a self-consuming loop.
We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models.
We present results for kernel density estimation, delivering nuanced insights such as the impact of mixed data training on error propagation.
arXiv Detail & Related papers (2024-02-19T02:08:09Z) - Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation [53.27596811146316]
Diffusion models operate over a sequence of timesteps instead of instantaneous input-output relationships in previous contexts.
We present Diffusion-TracIn that incorporates this temporal dynamics and observe that samples' loss gradient norms are highly dependent on timestep.
We introduce Diffusion-ReTrac as a re-normalized adaptation that enables the retrieval of training samples more targeted to the test sample of interest.
arXiv Detail & Related papers (2024-01-17T07:58:18Z) - Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models [52.1809084559048]
We propose a novel two-stage divide-and-conquer training strategy termed TDC Training.
It groups timesteps based on task similarity and difficulty, assigning highly customized denoising models to each group, thereby enhancing the performance of diffusion models.
While two-stage training avoids the need to train each model separately, the total training cost is even lower than training a single unified denoising model.
arXiv Detail & Related papers (2023-12-20T03:32:58Z) - The Journey, Not the Destination: How Data Guides Diffusion Models [75.19694584942623]
Diffusion models trained on large datasets can synthesize photo-realistic images of remarkable quality and diversity.
We propose a framework that: (i) provides a formal notion of data attribution in the context of diffusion models, and (ii) allows us to counterfactually validate such attributions.
arXiv Detail & Related papers (2023-12-11T08:39:43Z) - MissDiff: Training Diffusion Models on Tabular Data with Missing Values [29.894691645801597]
This work presents a unified and principled diffusion-based framework for learning from data with missing values.
We first observe that the widely adopted "impute-then-generate" pipeline may lead to a biased learning objective.
We prove the proposed method is consistent in learning the score of data distributions, and the proposed training objective serves as an upper bound for the negative likelihood in certain cases.
arXiv Detail & Related papers (2023-07-02T03:49:47Z) - FairIF: Boosting Fairness in Deep Learning via Influence Functions with
Validation Set Sensitive Attributes [51.02407217197623]
We propose a two-stage training algorithm named FAIRIF.
It minimizes the loss over the reweighted data set where the sample weights are computed.
We show that FAIRIF yields models with better fairness-utility trade-offs against various types of bias.
arXiv Detail & Related papers (2022-01-15T05:14:48Z) - Reconstructing Training Data from Diverse ML Models by Ensemble
Inversion [8.414622657659168]
Model Inversion (MI), in which an adversary abuses access to a trained Machine Learning (ML) model, has attracted increasing research attention.
We propose an ensemble inversion technique that estimates the distribution of original training data by training a generator constrained by an ensemble of trained models.
We achieve high quality results without any dataset and show how utilizing an auxiliary dataset that's similar to the presumed training data improves the results.
arXiv Detail & Related papers (2021-11-05T18:59:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.