A Bayesian Information-Theoretic Approach to Data Attribution

• URL: http://arxiv.org/abs/2604.03858v2
• Date: Wed, 08 Apr 2026 22:03:38 GMT
• Title: A Bayesian Information-Theoretic Approach to Data Attribution
• Abstract summary: Training Data Attribution seeks to trace model predictions back to influential training examples.<n>We approximate information loss using a Gaussian Process surrogate built from tangent features.<n>Experiments show our method scales to modern architectures while bridging principled measures with practice.
• Score: 7.908887001497405
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training Data Attribution (TDA) seeks to trace model predictions back to influential training examples, enhancing interpretability and safety. We formulate TDA as a Bayesian information-theoretic problem: subsets are scored by the information loss they induce - the entropy increase at a query when removed. This criterion credits examples for resolving predictive uncertainty rather than label noise. To scale to modern networks, we approximate information loss using a Gaussian Process surrogate built from tangent features. We show this aligns with classical influence scores for single-example attribution while promoting diversity for subsets. For even larger-scale retrieval, we relax to an information-gain objective and add a variance correction for scalable attribution in vector databases. Experiments show competitive performance on counterfactual sensitivity, ground-truth retrieval and coreset selection, showing that our method scales to modern architectures while bridging principled measures with practice.

Related papers

• Daunce: Data Attribution through Uncertainty Estimation [7.809316632545256]
  Training data attribution methods aim to identify which training examples influence a model's predictions on specific test data most.<n> Gradient-based TDA methods rely on gradients and second-order information, limiting their applicability at scale.<n>We introduce Daunce - a simple yet effective data attribution approach through uncertainty estimation.
  arXiv  Detail & Related papers  (2025-05-29T08:08:38Z)
• What is Adversarial Training for Diffusion Models? [4.71482540145286]
  We show that adversarial training (AT) for diffusion models (DMs) fundamentally differs from classifiers.<n>AT is a way to enforce smoothness in the diffusion flow, improving to outliers and corrupted data.<n>We rigorously evaluate our approach with proof-of-concept datasets with known distributions in low- and high-dimensional space.
  arXiv  Detail & Related papers  (2025-05-27T20:32:28Z)
• Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
  We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture.<n>We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
  arXiv  Detail & Related papers  (2024-09-20T07:41:47Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• On Counterfactual Data Augmentation Under Confounding [30.76982059341284]
  Counterfactual data augmentation has emerged as a method to mitigate confounding biases in the training data. These biases arise due to various observed and unobserved confounding variables in the data generation process. We show how our simple augmentation method helps existing state-of-the-art methods achieve good results.
  arXiv  Detail & Related papers  (2023-05-29T16:20:23Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Variational Classification [51.2541371924591]
  We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders. Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency. We induce a chosen latent distribution, instead of the implicit assumption found in a standard softmax layer.
  arXiv  Detail & Related papers  (2023-05-17T17:47:19Z)
• Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck [77.37409441129995]
  In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition. We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training. We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
  arXiv  Detail & Related papers  (2023-03-24T16:03:21Z)
• Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
  Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data. We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
  arXiv  Detail & Related papers  (2023-03-06T14:49:59Z)
• Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems [9.660129425150926]
  Cross entropy loss can easily lead us to find models which demonstrate severe overfitting behavior. In this paper, we prove that the existing cross entropy loss minimization for training DNN classifiers essentially learns the conditional entropy of the underlying data distribution. We propose a mutual information learning framework where we train DNN classifiers via learning the mutual information between the label and input.
  arXiv  Detail & Related papers  (2022-10-03T15:09:19Z)
• Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classification [2.922007656878633]
  We propose a new clustering method based on Variational Bayesian inference, further improved by Adaptive Dimension Reduction. Our proposed method significantly improves accuracy in the realistic unbalanced transductive setting on various Few-Shot benchmarks.
  arXiv  Detail & Related papers  (2022-09-18T10:29:02Z)
• 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)
• Self-Certifying Classification by Linearized Deep Assignment [65.0100925582087]
  We propose a novel class of deep predictors for classifying metric data on graphs within PAC-Bayes risk certification paradigm. Building on the recent PAC-Bayes literature and data-dependent priors, this approach enables learning posterior distributions on the hypothesis space.
  arXiv  Detail & Related papers  (2022-01-26T19:59:14Z)

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.