mlsanityData to 14 Oct 2026

Representer Point Selection for Explaining Deep Neural Networks

arXiv 1811.09720 ↗First posted 23 Nov 2018cs.LG stat.MLcited by 187

Not on the map. Why?

Abstract (arXiv)

We propose to explain the predictions of a deep neural network, by pointing to the set of what we call representer points in the training set, for a given test point prediction. Specifically, we show that we can decompose the pre-activation prediction of a neural network into a linear combination of activations of training points, with the weights corresponding to what we call representer values, which thus capture the importance of that training point on the learned parameters of the network. But it provides a deeper understanding of the network than simply training point influence: with positive representer values corresponding to excitatory training points, and negative values corresponding to inhibitory points, which as we show provides considerably more insight. Our method is also much more scalable, allowing for real-time feedback in a manner not feasible with influence functions.

Key facts. Cited by 187 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 35; 2022: 27; 2023: 31; 2024: 36; 2025: 33; 2026: 25.

187 papers.

Sort:

By area:

  1. 2023Explainability for Large Language Models: A Surveycited by 333
  2. 2023TRAK: Attributing Model Behavior at Scalecited by 283
  3. 2022Datamodels: Predicting Predictions from Training Datacited by 189
  4. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 156
  5. 2022If Influence Functions are the Answer, Then What is the Question?cited by 144
  6. 2022Training Data Influence Analysis and Estimation: A Surveycited by 135
  7. 2021Scaling Up Influence Functionscited by 132
  8. 2021Human-Centered Explainable AI (XAI): From Algorithms to User Experiencescited by 123
  9. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  10. 2021Towards a Science of Human-AI Decision Making: A Survey of Empirical Studiescited by 86
  11. 2021Input Similarity from the Neural Network Perspectivecited by 79
  12. 2023Fast Model Debias with Machine Unlearningcited by 72
38 more
  1. 2022"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interactioncited by 63
  2. 2022Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlationcited by 59
  3. 2022PUMA: Performance Unchanged Model Augmentation for Training Data Removalcited by 58
  4. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 53
  5. 2023Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runscited by 53
  6. 2023SHAP-IQ: Unified Approximation of any-order Shapley Interactionscited by 51
  7. 2022Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experimentscited by 50
  8. 2021Interactive Label Cleaning with Example-based Explanationscited by 49
  9. 2023Intriguing Properties of Data Attribution on Diffusion Modelscited by 47
  10. 2023The Journey, Not the Destination: How Data Guides Diffusion Modelscited by 43
  11. 2021Revisiting Methods for Finding Influential Examplescited by 39
  12. 2021HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networkscited by 38
  13. 2021Combining Feature and Instance Attribution to Detect Artifactscited by 38
  14. 2021DISSECT: Disentangled Simultaneous Explanations via Concept Traversalscited by 37
  15. 2023Self-Influence Guided Data Reweighting for Language Model Pre-trainingcited by 37
  16. 2021An Empirical Comparison of Instance Attribution Methods for NLPcited by 35
  17. 2022First is Better Than Last for Language Data Influencecited by 34
  18. 2022ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Datacited by 34
  19. 2024Training Data Attribution via Approximate Unrolled Differentiationcited by 34
  20. 2022Identifying a Training-Set Attack's Target Using Renormalized Influence Estimationcited by 32
  21. 2024Most Influential Subset Selection: Challenges, Promises, and Beyondcited by 32
  22. 2021Explaining Latent Representations with a Corpus of Examplescited by 30
  23. 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30
  24. 2021Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updatescited by 27
  25. 2022Data-Efficient Finetuning Using Cross-Task Nearest Neighborscited by 26
  26. 2022Human-Centered Concept Explanations for Neural Networkscited by 23
  27. 2022Understanding Influence Functions and Datamodels via Harmonic Analysiscited by 23
  28. 2024Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Modelscited by 22
  29. 2021Understanding Instance-based Interpretability of Variational Auto-Encoderscited by 21
  30. 2026OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iterationcited by 21
  31. 2022Challenges in Applying Explainability Methods to Improve the Fairness of NLP Modelscited by 20
  32. 2022Concept Gradient: Concept-based Interpretation Without Linear Assumptioncited by 20
  33. 2023Identification of Negative Transfers in Multitask Learning Using Surrogate Modelscited by 20
  34. 2024Token-wise Influential Training Data Retrieval for Large Language Modelscited by 20
  35. 2022Attribute Prototype Network for Any-Shot Learningcited by 19
  36. 2022Use-Case-Grounded Simulations for Explanation Evaluationcited by 19
  37. 2024Evolving Interpretable Visual Classifiers with Large Language Modelscited by 18
  38. 2024textttdattri: A Library for Efficient Data Attributioncited by 18

50 most cited of 187 All 187 (JSON)