mlsanityData to 14 Oct 2026

HyperGAN: A Generative Model for Diverse, Performant Neural Networks

arXiv 1901.11058 ↗First posted 30 Jan 2019cs.LG stat.MLcited by 51

Not on the map. Why?

Abstract (arXiv)

Standard neural networks are often overconfident when presented with data outside the training distribution. We introduce HyperGAN, a new generative model for learning a distribution of neural network parameters. HyperGAN does not require restrictive assumptions on priors, and networks sampled from it can be used to quickly create very large and diverse ensembles. HyperGAN employs a novel mixer to project prior samples to a latent space with correlated dimensions, and samples from the latent space are then used to generate weights for each layer of a deep neural network. We show that HyperGAN can learn to generate parameters which label the MNIST and CIFAR-10 datasets with competitive performance to fully supervised learning, while learning a rich distribution of effective parameters. We also show that HyperGAN can also provide better uncertainty estimates than standard ensembles by evaluating on out of distribution data as well as adversarial examples.

Key facts. Cited by 51 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 14; 2023: 6; 2024: 13; 2025: 6; 2026: 4.

51 papers.

Sort:

By area:

  1. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  2. 2021Parameter Prediction for Unseen Deep Architecturescited by 89
  3. 2022Learning to Learn with Generative Models of Neural Network Checkpointscited by 86
  4. 2021Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalizationcited by 83
  5. 2022Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weightscited by 64
  6. 2022HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learningcited by 55
  7. 2024Towards Scalable and Versatile Weight Space Learningcited by 41
  8. 2022Model Zoos: A Dataset of Diverse Populations of Neural Network Modelscited by 39
  9. 2024Diffusion-Based Neural Network Weights Generationcited by 39
  10. 2021Recomposing the Reinforcement Learning Building Blocks with Hypernetworkscited by 35
  11. 2022Learning the Effect of Registration Hyperparameters with HyperMorphcited by 35
  12. 2023Conditional Denoising Diffusion for Sequential Recommendationcited by 23
38 more
  1. 2024HyperFast: Instant Classification for Tabular Datacited by 22
  2. 2023HyperINR: A Fast and Predictive Hypernetwork for Implicit Neural Representations via Knowledge Distillationcited by 19
  3. 2023Principled Weight Initialization for Hypernetworkscited by 19
  4. 2021HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworkscited by 18
  5. 2022DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple Domainscited by 15
  6. 2023Magnitude Invariant Parametrizations Improve Hypernetwork Learningcited by 14
  7. 2022Federated Learning with Uncertainty via Distilled Predictive Distributionscited by 12
  8. 2022Hyper-Representations for Pre-Training and Transfer Learningcited by 12
  9. 2024ModelGPT: Unleashing LLM's Capabilities for Tailored Model Generationcited by 11
  10. 2024CLIPtone: Unsupervised Learning for Text-based Image Tone Adjustmentcited by 10
  11. 2021Dense Uncertainty Estimationcited by 9
  12. 2022Meta-Learning via Classifier(-free) Diffusion Guidancecited by 9
  13. 2024XReal: Realistic Anatomy and Pathology-Aware X-ray Generation via Controllable Diffusion Modelcited by 8
  14. 2021Meta Internal Learningcited by 7
  15. 2023HyperNeRFGAN: Hypernetwork approach to 3D NeRF GANcited by 7
  16. 2024Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Surveycited by 6
  17. 2025Structure Is Not Enough: Leveraging Behavior for Neural Network Weight Reconstructioncited by 6
  18. 2026DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weightscited by 5
  19. 2022Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attackscited by 4
  20. 2022Oracle Analysis of Representations for Deep Open Set Detectioncited by 3
  21. 2022PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inferencecited by 3
  22. 2024Conditional Pseudo-Reversible Normalizing Flow for Surrogate Modeling in Quantifying Uncertainty Propagationcited by 3
  23. 2025Instruction-Guided Autoregressive Neural Network Parameter Generationcited by 3
  24. 2025A Model Zoo of Vision Transformerscited by 3
  25. 2022Sardino: Ultra-Fast Dynamic Ensemble for Secure Visual Sensing at Mobile Edgecited by 2
  26. 2022Meta-Ensemble Parameter Learningcited by 2
  27. 2024Unleash Graph Neural Networks from Heavy Tuningcited by 2
  28. 2024Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKAcited by 2
  29. 2025Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approachcited by 2
  30. 2024Recall-Oriented Continual Learning with Generative Adversarial Meta-Modelcited by 1
  31. 2024Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuningcited by 1
  32. 2025Leveraging Hypernetworks and Learnable Kernels for Consumer Energy Forecasting Across Diverse Consumer Typescited by 1
  33. 2025GenUQ: Predictive Uncertainty Estimates via Generative Hyper-Networkscited by 1
  34. 2026Parametric Quantum State Tomography with HyperRBMscited by 1
  35. 2021MinConvNets: A new class of multiplication-less Neural Networkscited by 0
  36. 2021Graceful Degradation and Related Fieldscited by 0
  37. 2024Hyper-Representations: Learning from Populations of Neural Networkscited by 0
  38. 2026Hierarchical Shift Mixing -- Beyond Dense Attention in Transformerscited by 0

50 most cited of 51 All 51 (JSON)