mlsanityData to 14 Oct 2026

Learning to Weight Parameters for Training Data Attribution

arXiv 2506.05647 ↗First posted 6 Jun 2025cs.LG cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We study gradient-based data attribution, aiming to identify which training examples most influence a given output. Existing methods for this task either treat network parameters uniformly or rely on implicit weighting derived from Hessian approximations, which do not fully model functional heterogeneity of network parameters. To address this, we propose a method to explicitly learn parameter importance weights directly from data, without requiring annotated labels. Our approach improves attribution accuracy across diverse tasks, including image classification, language modeling, and diffusion, and enables fine-grained attribution for concepts like subject and style.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 51 of its 59 references that are in the map. First posted on arXiv 6 Jun 2025.

Builds on

51 of 59 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2024The Llama 3 Herd of Modelscited by 14,715
  7. 2020Denoising Diffusion Implicit Modelscited by 9,781
  8. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  10. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  11. 2022Classifier-Free Diffusion Guidancecited by 5,847
  12. 2024GPT-4o System Cardcited by 4,588
38 more
  1. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  2. 2016Pointer Sentinel Mixture Modelscited by 3,096
  3. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  4. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 906
  5. 2023A Simple and Effective Pruning Approach for Large Language Modelscited by 800
  6. 2023Extracting Training Data from Diffusion Modelscited by 732
  7. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 650
  8. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 629
  9. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 580
  10. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 497
  11. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 424
  12. 2021Multimodal datasets: misogyny, pornography, and malignant stereotypescited by 327
  13. 2023Studying Large Language Model Generalization with Influence Functionscited by 326
  14. 2023SqueezeLLM: Dense-and-Sparse Quantizationcited by 294
  15. 2023TRAK: Attributing Model Behavior at Scalecited by 283
  16. 2019Towards Efficient Data Valuation Based on the Shapley Valuecited by 281
  17. 2020The Lottery Ticket Hypothesis for Pre-trained BERT Networkscited by 275
  18. 2023Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Timecited by 252
  19. 2023FreeU: Free Lunch in Diffusion U-Netcited by 196
  20. 2022Datamodels: Predicting Predictions from Training Datacited by 189
  21. 2018Representer Point Selection for Explaining Deep Neural Networkscited by 187
  22. 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 154
  23. 2021Scaling Up Influence Functionscited by 132
  24. 2024What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functionscited by 94
  25. 2021Input Similarity from the Neural Network Perspectivecited by 79
  26. 2023DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Modelscited by 79
  27. 2022The ArtBench Dataset: Benchmarking Generative Models with Artworkscited by 64
  28. 2023Compressing LLMs: The Truth is Rarely Pure and Never Simplecited by 62
  29. 2023Intriguing Properties of Data Attribution on Diffusion Modelscited by 47
  30. 2023The Journey, Not the Destination: How Data Guides Diffusion Modelscited by 43
  31. 2024Scalable Influence and Fact Tracing for Large Language Model Pretrainingcited by 42
  32. 2022First is Better Than Last for Language Data Influencecited by 34
  33. 2024Influence Functions for Scalable Data Attribution in Diffusion Modelscited by 33
  34. 2024Data Attribution for Text-to-Image Models by Unlearning Synthesized Imagescited by 22
  35. 2024Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Modelscited by 22
  36. 2024Unlearning Traces the Influential Training Data of Language Modelscited by 18
  37. 2024Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Modelscited by 9
  38. 2025Does Editing Provide Evidence for Localization?cited by 7

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Sensitivity Analysis for Diffusion Modelscited by 1
  2. 2026Do Neural Networks Preserve Case Structure? Case-Based Decomposition, Interpretation, and Decision Consistencycited by 1
  3. 2026Importance-Aware OBS Pruning for Diffusion Modelscited by 0