mlsanityData to 14 Oct 2026

Dataset Distillation Using Parameter Pruning

arXiv 2209.14609 ↗First posted 29 Sep 2022cs.CV cs.AI cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

In this study, we propose a novel dataset distillation method based on parameter pruning. The proposed method can synthesize more robust distilled datasets and improve distillation performance by pruning difficult-to-match parameters during the distillation process. Experimental results on two benchmark datasets show the superiority of the proposed method.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 29 Sep 2022.

Builds on

24 of 35 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  5. 2018An Empirical Study of Example Forgetting during Deep Neural Network Learningcited by 678
  6. 2020Dataset Condensation with Gradient Matchingcited by 516
  7. 2022Dataset Distillation by Matching Training Trajectoriescited by 442
  8. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  9. 2021Dataset Condensation with Distribution Matchingcited by 365
  10. 2021Dataset Condensation with Differentiable Siamese Augmentationcited by 291
  11. 2018Dataset Distillationcited by 230
  12. 2021Dataset Distillation with Infinitely Wide Convolutional Networkscited by 218
12 more
  1. 2021Self-supervised Pretraining of Visual Features in the Wildcited by 198
  2. 2022Privacy for Free: How does Dataset Condensation Help Privacy?cited by 120
  3. 2019Soft-Label Dataset Distillation and Text Dataset Distillationcited by 107
  4. 2019Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Datacited by 104
  5. 2020Flexible Dataset Distillation: Learn Labels Instead of Imagescited by 91
  6. 2017Practical Coreset Constructions for Machine Learningcited by 78
  7. 2021Soft-Label Anonymous Gastric X-ray Image Distillationcited by 51
  8. 2022Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environmentscited by 49
  9. 2022Sample Condensation in Online Continual Learningcited by 31
  10. 2021Condensed Composite Memory Continual Learningcited by 20
  11. 2022Self-Knowledge Distillation based Self-Supervised Learning for Covid-19 Detection from Chest X-Ray Imagescited by 13
  12. 2022TriBYOL: Triplet BYOL for Self-Supervised Representation Learningcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 9; 2025: 7; 2026: 6.

27 papers.

Sort:

By area:

  1. 2022Minimizing the Accumulated Trajectory Error to Improve Dataset Distillationcited by 142
  2. 2023Dataset Distillation: A Comprehensive Reviewcited by 127
  3. 2024Dataset Distillation by Automatic Training Trajectoriescited by 26
  4. 2025The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutionscited by 26
  5. 2024Multi-modal Vision Pre-training for Medical Image Analysiscited by 23
  6. 2024Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectorycited by 21
  7. 2024Multisize Dataset Condensationcited by 19
  8. 2024Importance-Aware Adaptive Dataset Distillationcited by 18
  9. 2024Generative Dataset Distillation: Balancing Global Structure and Local Detailscited by 18
  10. 2025Hyperbolic Dataset Distillationcited by 15
  11. 2024Dataset Quantization with Active Learning based Adaptive Samplingcited by 13
  12. 2025Diversity-Driven Generative Dataset Distillation Based on Diffusion Model with Self-Adaptive Memorycited by 10
15 more
  1. 2023Dataset Distillation in Latent Spacecited by 8
  2. 2025Task-Specific Generative Dataset Distillation with Difficulty-Guided Samplingcited by 8
  3. 2025Efficient Multimodal Dataset Distillation via Generative Modelscited by 7
  4. 2025Decoupled Audio-Visual Dataset Distillationcited by 7
  5. 2024CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecastingcited by 6
  6. 2026A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Designcited by 5
  7. 2023Bayesian Pseudo-Coresets via Contrastive Divergencecited by 4
  8. 2022Boosting Automatic COVID-19 Detection Performance with Self-Supervised Learning and Batch Knowledge Ensemblingcited by 3
  9. 2024Tackling Data Heterogeneity in Federated Time Series Forecastingcited by 3
  10. 2026FD2: A Dedicated Framework for Fine-Grained Dataset Distillationcited by 3
  11. 2025Distill Video Datasets into Imagescited by 0
  12. 2026Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integrationcited by 0
  13. 2026SAS: Semantic-aware Sampling for Generative Dataset Distillationcited by 0
  14. 2026DeCO: Discriminative Evidence Composition for Fine-Grained Dataset Distillationcited by 0
  15. 2026PSM: Dataset Distillation Based on Precise Statistical Matching by Difficultycited by 0