Papers › HyperNetworks

HyperNetworks

27 Sep 2016arXiv:1609.09106archive 2025-07-28

David Ha, Andrew Dai, Quoc V. Le

This work explores hypernetworks: an approach of using a one network, also known as a hypernetwork, to generate the weights for another network. Hypernetworks provide an abstraction that is similar to what is found in nature: the relationship between a genotype - the hypernetwork - and a phenotype - the main network. Though they are also reminiscent of HyperNEAT in evolution, our hypernetworks are trained end-to-end with backpropagation and thus are usually faster. The focus of this work is to make hypernetworks useful for deep convolutional networks and long recurrent networks, where hypernetworks can be viewed as relaxed form of weight-sharing across layers. Our main result is that hypernetworks can generate non-shared weights for LSTM and achieve near state-of-the-art results on a variety of sequence modelling tasks including character-level language modelling, handwriting generation and neural machine translation, challenging the weight-sharing paradigm for recurrent networks. Our results also show that hypernetworks applied to convolutional networks still achieve respectable results for image recognition tasks compared to state-of-the-art baseline models while requiring fewer learnable parameters.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1609.09106")

Code

Syntology Ran 3 of 4 code samples harvested from 2 repositories linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong.

By repository: community (archive-listed): 4 samples from 2 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cellistigs/ensemble_attention mentioned on GitHubpytorch report
chrhenning/hypnettorch mentioned on GitHubpytorch report
g1910/HyperNetworks mentioned on GitHubpytorchGPL-3.0 report
gtegner/hyper-gan mentioned on GitHubpytorch report
pennfranc/hypnettorch mentioned on GitHubpytorch report
shyamsn97/hyper-nn mentioned on GitHubjax report
tjuhaoxiaotian/pymarl3 mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

4 samples harvested; 3 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
1unverified

Licence: 3 of the 4 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

create_param_tree shyamsn97/hyper-nn/hypernn/jax/hypernet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 8143f1c0cbd2ab4e · report
get_entropy gtegner/hyper-gan/hypergan_utils.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 410618de180f045a · report
true_data gtegner/hyper-gan/hypergan_utils.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 03e2fdfe356c35f0 · report
plot_classification gtegner/hyper-gan/hypergan_utils.py community (archive-listed) unverified no licence file found · pointer only · 15ad5ae30ec820ea · report

Tasks

Handwriting generationLanguage ModellingMachine TranslationTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling Penn Treebank (Character Level) 2-layer Norm HyperLSTM Bit per Character (BPC) 1.219 #14 of 20 Archive leaderboard report
Language Modelling Penn Treebank (Character Level) 2-layer Norm HyperLSTM Number of params 14.4M #14 of 20 Archive leaderboard report
Language Modelling enwik8 Hypernetworks Bit per Character (BPC) 1.34 #40 of 42 Archive leaderboard report
Language Modelling enwik8 Hypernetworks Number of params 27M #40 of 42 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: HyperNetwork

HyperNetwork

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections