mlsanityData to 7 Oct 2026

Towards a Neural Statistician

arXiv 1606.02185 ↗First posted 7 Jun 2016stat.ML cs.LGcited by 119

Not on the map. Why?

Abstract (arXiv)

An efficient learner is one who reuses what they already know to tackle a new problem. For a machine learner, this means understanding the similarities amongst datasets. In order to do this, one must take seriously the idea of working with datasets, rather than datapoints, as the key objects to model. Towards this goal, we demonstrate an extension of a variational autoencoder that can learn a method for computing representations, or statistics, of datasets in an unsupervised fashion. The network is trained to produce statistics that encapsulate a generative model for each dataset. Hence the network enables efficient learning from new datasets for both unsupervised and supervised tasks. We show that we are able to learn statistics that can be used for: clustering datasets, transferring generative models to new datasets, selecting representative samples of datasets and classifying previously unseen classes. We refer to our model as a neural statistician, and by this we mean a neural network that can learn to compute summary statistics of datasets without supervision.

Key facts. Cited by 119 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 42; 2022: 21; 2023: 21; 2024: 16; 2025: 11; 2026: 8.

119 papers.

Sort:

By area:

  1. 2021Transformers in Vision: A Surveycited by 1,009
  2. 2022Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learningcited by 357
  3. 2021Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Designcited by 103
  4. 2021Proximal Optimal Transport Modeling of Population Dynamicscited by 91
  5. 2021SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Datacited by 78
  6. 2021What to Pre-Train on? Efficient Intermediate Task Selectioncited by 62
  7. 2021Neural ODE Processescited by 57
  8. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 57
  9. 2021Bayesian Learning via Neural Schr"odinger-F"ollmer Flowscited by 56
  10. 2021Few-shot Conformal Prediction with Auxiliary Taskscited by 53
  11. 2022Self-Supervised Vision Transformers Learn Visual Concepts in Histopathologycited by 49
  12. 2023A General-Purpose Self-Supervised Model for Computational Pathologycited by 42
38 more
  1. 2021You Never Cluster Alonecited by 38
  2. 2022Few-Shot Diffusion Modelscited by 37
  3. 2021Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertisingcited by 31
  4. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  5. 2021The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learningcited by 23
  6. 2022The Neural Process Family: Survey, Applications and Perspectivescited by 23
  7. 2022Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learningcited by 23
  8. 2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
  9. 2021Learning Prototype-oriented Set Representations for Meta-Learningcited by 19
  10. 2021Amortized Variational Inference for Simple Hierarchical Modelscited by 19
  11. 2021Few-Shot Learning with Class Imbalancecited by 18
  12. 2021Neural Recursive Belief States in Multi-Agent Reinforcement Learningcited by 18
  13. 2021TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptationcited by 17
  14. 2021Few-Shot Learning with a Strong Teachercited by 16
  15. 2022Neural Processes with Stochastic Attention: Paying more attention to the context datasetcited by 16
  16. 2022Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributionscited by 14
  17. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  18. 2024Zero-shot Imputation with Foundation Inference Models for Dynamical Systemscited by 13
  19. 2025Long Context In-Context Compression by Getting to the Gist of Gistingcited by 12
  20. 2021What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Datacited by 10
  21. 2021Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptationcited by 10
  22. 2023Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?cited by 10
  23. 2022Diversity vs. Recognizability: Human-like generalization in one-shot generative modelscited by 9
  24. 2022Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognitioncited by 9
  25. 2023Meta-learning in healthcare: A surveycited by 9
  26. 2023Phoneme Hallucinator: One-shot Voice Conversion via Set Expansioncited by 9
  27. 2021Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learningcited by 8
  28. 2021Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awarenesscited by 8
  29. 2022Hierarchical Transformer for Survival Prediction Using Multimodality Whole Slide Images and Genomicscited by 8
  30. 2023Episodic Multi-Task Learning with Heterogeneous Neural Processescited by 8
  31. 2025FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulationcited by 8
  32. 2021On the Importance of Firth Bias Reduction in Few-Shot Classificationcited by 7
  33. 2022Stochastic Deep Networks with Linear Competing Units for Model-Agnostic Meta-Learningcited by 7
  34. 2022Transductive Decoupled Variational Inference for Few-Shot Classificationcited by 7
  35. 2023Few-shot Action Recognition via Intra- and Inter-Video Information Maximizationcited by 7
  36. 2023Approximating Human-Like Few-shot Learning with GPT-based Compressioncited by 7
  37. 2023Postprocessing of Ensemble Weather Forecasts Using Permutation-invariant Neural Networkscited by 7
  38. 2025In-Context Learning of Stochastic Differential Equations with Foundation Inference Modelscited by 7

50 most cited of 119 All 119 (JSON)