# An open dataset of neural networks for hypernetwork research

arXiv: https://arxiv.org/abs/2507.15869 · HTML: https://mlsanity.com/paper/2507.15869/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 15 Jul 2025.

## Builds on (most cited first, 17 of 17)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Graph HyperNetworks for Neural Architecture Search](https://mlsanity.com/paper/1810.05749/) (2018)
- [Predicting Neural Network Accuracy from Weights](https://mlsanity.com/paper/2002.11448/) (2020)
- [Equivariant Architectures for Learning in Deep Weight Spaces](https://mlsanity.com/paper/2301.12780/) (2023)
- [A Brief Review of Hypernetworks in Deep Learning](https://mlsanity.com/paper/2306.06955/) (2023)
- [Parameter Prediction for Unseen Deep Architectures](https://mlsanity.com/paper/2110.13100/) (2021)
- [Classifying the classifier: dissecting the weight space of neural networks](https://mlsanity.com/paper/2002.05688/) (2020)
- [Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights](https://mlsanity.com/paper/2209.14733/) (2022)
- [Scientific Machine Learning Benchmarks](https://mlsanity.com/paper/2110.12773/) (2021)
- [Continual Model-Based Reinforcement Learning with Hypernetworks](https://mlsanity.com/paper/2009.11997/) (2020)
- [Model Zoos: A Dataset of Diverse Populations of Neural Network Models](https://mlsanity.com/paper/2209.14764/) (2022)
- [Recomposing the Reinforcement Learning Building Blocks with Hypernetworks](https://mlsanity.com/paper/2106.06842/) (2021)
- [AlphaEvolve: A Learning Framework to Discover Novel Alphas in Quantitative Investment](https://mlsanity.com/paper/2103.16196/) (2021)
- [Unreflected Use of Tabular Data Repositories Can Undermine Research Quality](https://mlsanity.com/paper/2503.09159/) (2025)
- [Hyper-CL: Conditioning Sentence Representations with Hypernetworks](https://mlsanity.com/paper/2403.09490/) (2024)
- [Analysis and prevention of AI-based phishing email attacks](https://mlsanity.com/paper/2405.05435/) (2024)

## Abstract (arXiv)

Despite the transformative potential of AI, the concept of neural networks that can produce other neural networks by generating model weights (hypernetworks) has been largely understudied. One of the possible reasons is the lack of available research resources that can be used for the purpose of hypernetwork research. Here we describe a dataset of neural networks, designed for the purpose of hypernetworks research. The dataset includes 104 LeNet-5 neural networks trained for binary image classification separated into 10 classes, such that each class contains 1,000 different neural networks that can identify a certain ImageNette V2 class from all other classes. A computing cluster of over 104 cores was used to generate the dataset. Basic classification results show that the neural networks can be classified with accuracy of 72.0%, indicating that the differences between the neural networks can be identified by supervised machine learning algorithms. The ultimate purpose of the dataset is to enable hypernetworks research. The dataset and the code that generates it are open and accessible to the public.