mlsanityData to 7 Oct 2026

Conditional Neural Processes

arXiv 1807.01613 ↗First posted 4 Jul 2018cs.LG stat.MLcited by 421

Not on the map. Why?

Abstract (arXiv)

Deep neural networks excel at function approximation, yet they are typically trained from scratch for each new function. On the other hand, Bayesian methods, such as Gaussian Processes (GPs), exploit prior knowledge to quickly infer the shape of a new function at test time. Yet GPs are computationally expensive, and it can be hard to design appropriate priors. In this paper we propose a family of neural models, Conditional Neural Processes (CNPs), that combine the benefits of both. CNPs are inspired by the flexibility of stochastic processes such as GPs, but are structured as neural networks and trained via gradient descent. CNPs make accurate predictions after observing only a handful of training data points, yet scale to complex functions and large datasets. We demonstrate the performance and versatility of the approach on a range of canonical machine learning tasks, including regression, classification and image completion.

Key facts. Cited by 421 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 68; 2022: 74; 2023: 75; 2024: 61; 2025: 75; 2026: 67.

421 papers.

Sort:

By area:

  1. 2022What Can Transformers Learn In-Context? A Case Study of Simple Function Classescited by 700
  2. 2021Transformers Can Do Bayesian Inferencecited by 338
  3. 2022From data to functa: Your data point is a function and you can treat it like onecited by 183
  4. 2022Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modelingcited by 126
  5. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  6. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 112
  7. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  8. 2021Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Designcited by 103
  9. 2022CARD: Classification and Regression Diffusion Modelscited by 102
  10. 2022General-Purpose In-Context Learning by Meta-Learning Transformerscited by 102
  11. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  12. 2021Generative Models as Distributions of Functionscited by 89
38 more
  1. 2021Conservative Objective Models for Effective Offline Model-Based Optimizationcited by 87
  2. 2022Tutorial on amortized optimizationcited by 83
  3. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
  4. 2023PFNs4BO: In-Context Learning for Bayesian Optimizationcited by 70
  5. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  6. 2023GFlowNets for AI-Driven Scientific Discoverycited by 63
  7. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 60
  8. 2024A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)cited by 58
  9. 2021Neural ODE Processescited by 57
  10. 2022Neural Diffusion Processescited by 50
  11. 2022Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Expertscited by 50
  12. 2022Generalizing to New Physical Systems via Context-Informed Dynamics Modelcited by 49
  13. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  14. 2023A Closer Look at Few-shot Classification Againcited by 46
  15. 2025Do-PFN: In-Context Learning for Causal Effect Estimationcited by 46
  16. 2025CausalPFN: Amortized Causal Effect Estimation via In-Context Learningcited by 43
  17. 2021Offline Model-Based Optimization via Normalized Maximum Likelihood Estimationcited by 38
  18. 2022Few-Shot Diffusion Modelscited by 37
  19. 2022Generative Pretraining for Black-Box Optimizationcited by 36
  20. 2024Online Adaptation of Language Models with a Memory of Amortized Contextscited by 35
  21. 2021The Gaussian Neural Processcited by 34
  22. 2023A Survey on Knowledge Editing of Neural Networkscited by 34
  23. 2022Deep Depth Completion from Extremely Sparse Data: A Surveycited by 33
  24. 2024Active Evaluation Acquisition for Efficient LLM Benchmarkingcited by 33
  25. 2023Autoregressive Conditional Neural Processescited by 32
  26. 2023End-to-End Meta-Bayesian Optimisation with Transformer Neural Processescited by 31
  27. 2024Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodingscited by 31
  28. 2021Convolutional conditional neural processes for local climate downscalingcited by 29
  29. 2021Data-Driven Offline Optimization For Architecting Hardware Acceleratorscited by 29
  30. 2022Meta Optimal Transportcited by 28
  31. 2023Transfer Learning for Bayesian Optimization: A Surveycited by 27
  32. 2022Latent Bottlenecked Attentive Neural Processescited by 26
  33. 2024Learning to Defer to a Population: A Meta-Learning Approachcited by 26
  34. 2021NRTSI: Non-Recurrent Time Series Imputationcited by 25
  35. 2022Practical Conditional Neural Processes Via Tractable Dependent Predictionscited by 25
  36. 2022NP-Match: When Neural Processes meet Semi-Supervised Learningcited by 25
  37. 2022ProDMPs: A Unified Perspective on Dynamic and Probabilistic Movement Primitivescited by 25
  38. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25

50 most cited of 421 All 421 (JSON)