mlsanityData to 14 Oct 2026

Understanding Instance-based Interpretability of Variational Auto-Encoders

arXiv 2105.14203 ↗First posted 29 May 2021cs.LG stat.MLcited by 21

Not on the map. Why?

Abstract (arXiv)

Instance-based interpretation methods have been widely studied for supervised learning methods as they help explain how black box neural networks predict. However, instance-based interpretations remain ill-understood in the context of unsupervised learning. In this paper, we investigate influence functions [Koh and Liang, 2017], a popular instance-based interpretation method, for a class of deep generative models called variational auto-encoders (VAE). We formally frame the counter-factual question answered by influence functions in this setting, and through theoretical analysis, examine what they reveal about the impact of training samples on classical unsupervised learning methods. We then introduce VAE- TracIn, a computationally efficient and theoretically sound solution based on Pruthi et al. [2020], for VAEs. Finally, we evaluate VAE-TracIn on several real world datasets with extensive quantitative and qualitative analysis.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 27 of its 53 references that are in the map. First posted on arXiv 29 May 2021.

Builds on

27 of 53 references.

References · 27

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  5. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  6. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 629
  7. 2018Disentangling by Factorisingcited by 616
  8. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 580
  9. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  10. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 497
  11. 2020Approximate Data Deletion from Machine Learning Modelscited by 255
  12. 2018Representer Point Selection for Explaining Deep Neural Networkscited by 187
15 more
  1. 2019On the Accuracy of Influence Functions for Measuring Group Effectscited by 147
  2. 2019Data Valuation using Reinforcement Learningcited by 116
  3. 2019On Second-Order Group Influence Functions for Black-Box Predictionscited by 79
  4. 2019Data Cleansing for Models Trained with SGDcited by 67
  5. 2020A Non-Parametric Test to Detect Data-Copying in Generative Modelscited by 52
  6. 2018Interpreting Black Box Predictions using Fisher Kernelscited by 48
  7. 2020RelatIF: Identifying Explanatory Training Examples via Relative Influencecited by 28
  8. 2021Evaluating the Interpretability of Generative Models by Interactive Reconstructioncited by 17
  9. 2020Multi-Stage Influence Functioncited by 16
  10. 2021Estimating informativeness of samples with Smooth Unique Informationcited by 15
  11. 2020Teaching a GAN What Not to Learncited by 13
  12. 2017Optimal Sub-sampling with Influence Functionscited by 11
  13. 2021Influence Estimation for Generative Adversarial Networkscited by 11
  14. 2021Out-of-Distribution Generalization Analysis via Influence Functioncited by 11
  15. 2021Data Cleansing for Deep Neural Networks with Storage-efficient Approximation of Influence Functionscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 6; 2024: 4; 2025: 2; 2026: 1.

21 papers.

Sort:

By area:

  1. 2022Training Data Influence Analysis and Estimation: A Surveycited by 135
  2. 2021On Memorization in Probabilistic Deep Generative Modelscited by 60
  3. 2023Intriguing Properties of Data Attribution on Diffusion Modelscited by 47
  4. 2021Rethinking Influence Functions of Neural Networks in the Over-parameterized Regimecited by 26
  5. 2024Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Modelscited by 22
  6. 2022An Empirical Study of Memorization in NLPcited by 21
  7. 2022Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Treescited by 16
  8. 2022Label-Free Explainability for Unsupervised Modelscited by 14
  9. 2024Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimationcited by 14
  10. 2024Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspectivecited by 9
  11. 2022TracInAD: Measuring Influence for Anomaly Detectioncited by 8
  12. 2023Error Discovery by Clustering Influence Embeddingscited by 8
9 more
  1. 2023Prototypical Self-Explainable Models Without Re-trainingcited by 6
  2. 2024Exploring Latent Pathways: Enhancing the Interpretability of Autonomous Driving with a Variational Autoencodercited by 6
  3. 2023GMValuator: Similarity-based Data Valuation for Generative Modelscited by 5
  4. 2022Approximate Data Deletion in Generative Modelscited by 4
  5. 2023Trainable and Explainable Simplicial Map Neural Networkscited by 2
  6. 2023Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Modelscited by 1
  7. 2025A Comparative Analysis of Influence Signals for Data Debuggingcited by 0
  8. 2025IFFair: Influence Function-driven Sample Reweighting for Fair Classificationcited by 0
  9. 2026Distilling Diffusion Score Discrepancy for Efficient Training Data Attributioncited by 0