Distributional Training Data Attribution: What do Influence Functions Sample?

• URL: http://arxiv.org/abs/2506.12965v3
• Date: Sat, 25 Oct 2025 12:43:41 GMT
• Title: Distributional Training Data Attribution: What do Influence Functions Sample?
• Authors: Bruno Mlodozeniec, Isaac Reid, Sam Power, David Krueger, Murat Erdogdu, Richard E. Turner, Roger Grosse,
• Abstract summary: We introduce distributional training data attribution (d-TDA)<n>The goal of d-TDA is to predict how the distribution of model outputs depends upon the dataset.<n>We find that influence functions (IFs) are'secretly distributional'
• Score: 25.257922996567178
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Randomness is an unavoidable part of training deep learning models, yet something that traditional training data attribution algorithms fail to rigorously account for. They ignore the fact that, due to stochasticity in the initialisation and batching, training on the same dataset can yield different models. In this paper, we address this shortcoming through introducing distributional training data attribution (d-TDA), the goal of which is to predict how the distribution of model outputs (over training runs) depends upon the dataset. Intriguingly, we find that influence functions (IFs), a popular data attribution tool, are 'secretly distributional': they emerge from our framework as the limit to unrolled differentiation, without requiring restrictive convexity assumptions. This provides a new perspective on the effectiveness of IFs in deep learning. We demonstrate the practical utility of d-TDA in experiments, including improving data pruning for vision transformers and identifying influential examples with diffusion models.

Related papers

• Nonparametric Data Attribution for Diffusion Models [57.820618036556084]
  Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs.<n>We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images.
  arXiv  Detail & Related papers  (2025-10-16T03:37:16Z)
• Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical loss [0.4249842620609682]
  We build on the textitinvariant statistical loss (ISL) method introduced in citede2024training. We extend it to handle heavy-tailed and multivariate data distributions. We assess its performance in generative generative modeling and explore its potential as a pretraining technique for generative adversarial networks (GANs)
  arXiv  Detail & Related papers  (2024-10-29T10:27:50Z)
• Influence Functions for Scalable Data Attribution in Diffusion Models [52.92223039302037]
  Diffusion models have led to significant advancements in generative modelling.<n>Yet their widespread adoption poses challenges regarding data attribution and interpretability.<n>We develop an influence functions framework to address these challenges.
  arXiv  Detail & Related papers  (2024-10-17T17:59:02Z)
• Data Shapley in One Training Run [88.59484417202454]
  Data Shapley provides a principled framework for attributing data's contribution within machine learning contexts.<n>Existing approaches require re-training models on different data subsets, which is computationally intensive.<n>This paper introduces In-Run Data Shapley, which addresses these limitations by offering scalable data attribution for a target model of interest.
  arXiv  Detail & Related papers  (2024-06-16T17:09:24Z)
• Ask Your Distribution Shift if Pre-Training is Right for You [67.90850628695563]
  In practice, fine-tuning a pre-trained model improves robustness significantly in some cases but not at all in others.<n>We focus on two possible failure modes of models under distribution shift: poor extrapolation and biases in the training data.<n>Our study suggests that, as a rule of thumb, pre-training can help mitigate poor extrapolation but not dataset biases.
  arXiv  Detail & Related papers  (2024-02-29T23:46:28Z)
• Mixture Data for Training Cannot Ensure Out-of-distribution Generalization [21.801115344132114]
  We show that increasing the size of training data does not always lead to a reduction in the test generalization error. In this work, we quantitatively redefine OOD data as those situated outside the convex hull of mixed training data. Our proof of the new risk bound agrees that the efficacy of well-trained models can be guaranteed for unseen data.
  arXiv  Detail & Related papers  (2023-12-25T11:00:38Z)
• On the Connection between Pre-training Data Diversity and Fine-tuning Robustness [66.30369048726145]
  We find that the primary factor influencing downstream effective robustness is data quantity. We demonstrate our findings on pre-training distributions drawn from various natural and synthetic data sources.
  arXiv  Detail & Related papers  (2023-07-24T05:36:19Z)
• 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)
• Training Data Attribution for Diffusion Models [1.1733780065300188]
  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.
  arXiv  Detail & Related papers  (2023-06-03T18:36:12Z)
• Preserving Fairness in AI under Domain Shift [15.820660013260584]
  Existing algorithms for ensuring fairness in AI use a single-shot training strategy. We develop an algorithm to adapt a fair model to remain fair under domain shift.
  arXiv  Detail & Related papers  (2023-01-29T06:13:40Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Agree to Disagree: Diversity through Disagreement for Better Transferability [54.308327969778155]
  We propose D-BAT (Diversity-By-disAgreement Training), which enforces agreement among the models on the training data. We show how D-BAT naturally emerges from the notion of generalized discrepancy.
  arXiv  Detail & Related papers  (2022-02-09T12:03:02Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• Predicting with Confidence on Unseen Distributions [90.68414180153897]
  We connect domain adaptation and predictive uncertainty literature to predict model accuracy on challenging unseen distributions. We find that the difference of confidences (DoC) of a classifier's predictions successfully estimates the classifier's performance change over a variety of shifts. We specifically investigate the distinction between synthetic and natural distribution shifts and observe that despite its simplicity DoC consistently outperforms other quantifications of distributional difference.
  arXiv  Detail & Related papers  (2021-07-07T15:50:18Z)
• Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance [70.31427277842239]
  We introduce a novel debiasing method called confidence regularization. It discourages models from exploiting biases while enabling them to receive enough incentive to learn from all the training examples. We evaluate our method on three NLU tasks and show that, in contrast to its predecessors, it improves the performance on out-of-distribution datasets.
  arXiv  Detail & Related papers  (2020-05-01T11:22:55Z)

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.