Papers › PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions
PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions
Eleonora Grassucci, Aston Zhang, Danilo Comminiello
Hypercomplex neural networks have proven to reduce the overall number of parameters while ensuring valuable performance by leveraging the properties of Clifford algebras. Recently, hypercomplex linear layers have been further improved by involving efficient parameterized Kronecker products. In this paper, we define the parameterization of hypercomplex convolutional layers and introduce the family of parameterized hypercomplex neural networks (PHNNs) that are lightweight and efficient large-scale models. Our method grasps the convolution rules and the filter organization directly from data without requiring a rigidly predefined domain structure to follow. PHNNs are flexible to operate in any user-defined or tuned domain, from 1D to nD regardless of whether the algebra rules are preset. Such a malleability allows processing multidimensional inputs in their natural domain without annexing further dimensions, as done, instead, in quaternion neural networks for 3D inputs like color images. As a result, the proposed family of PHNNs operates with 1/n free parameters as regards its analog in the real domain. We demonstrate the versatility of this approach to multiple domains of application by performing experiments on various image datasets as well as audio datasets in which our method outperforms real and quaternion-valued counterparts. Full code is available at: https://github.com/eleGAN23/HyperNets.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2110.04176")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2110.04176", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2110.04176")
Code
Syntology 34 code samples harvested from 4 repositories linked to this paper: 28 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 0 violated, 23 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 2 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 32 samples from 3 repositories, 28 ran (24 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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
34 samples harvested: 28 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 0 violated, 23 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 5 of the 34 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
3e94054b554510ce · report
2c0bc31335e2f961 · report
e2e18700dc6ed1a8 · report
fixture: signature statistic:Tensor/2/float, curr_value:Tensor/2/float, momentum:float/0/float · returned Tensor · level recorded 2026-09-22 855253f62eb9802c · report
fixture: signature module:callable/0/?, name:str/0/str · returned Linear · level recorded 2026-09-24 8def708af5968cc7 · report
b9ef9bade0c9f9c8 · report
fixture: signature len_train:int/0/int, len_val:int/0/int, len_test:int/0/int, n:int/0/int · returned tuple · level recorded 2026-09-24 6760e9b0a1a4eea4 · report
fixture: signature len_train:int/0/int, len_val:int/0/int, len_test:int/0/int, n:int/0/int · returned tuple · level recorded 2026-09-24 d9d732f238cd29b2 · report
fixture: signature len_train:int/0/int, len_val:int/0/int, len_test:int/0/int, n:int/0/int · returned tuple · level recorded 2026-09-24 cb04204d244b0222 · report
fixture: signature val_loss:float/0/float, train_loss:float/0/float, min_val_loss:float/0/float, patience_epochs:int/0/int, epochs_no_improve:int/0/int · returned tuple · level recorded 2026-09-24 01423bbbb5930bbd · report
fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-24 250d2abbf60ffa77 · report
fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-24 917981cbd6f167d2 · report
fixture: signature input:Tensor/2/float, channel:int/0/int · returned Tensor · level recorded 2026-09-24 16d563ee991cd39f · report
fixture: signature logits:Tensor/2/float, target:int/0/int · returned Tensor · level recorded 2026-09-22 55dc256ba1c04149 · report
fixture: signature nets:SimpleNets/0/?, args:SimpleArgs/0/?, x_real:Tensor/2/float, y_org:Tensor/1/int, y_trg:Tensor/1/int, z_trg:Tensor/2/float, x_ref:NoneType/0/?, masks:NoneType/0/? · returned tuple · level recorded 2026-09-24 d0c7af72cd606f53 · report
fixture: signature nets:Nets/0/?, args:Args/0/?, x_real:Tensor/4/float, y_org:Tensor/1/int, y_trg:Tensor/1/int, z_trgs:tuple/1/Tensor, x_refs:NoneType/0/?, masks:NoneType/0/? · returned tuple · level recorded 2026-09-24 470f567ca3e3fb39 · report
fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24 cc1c58c9ca8943e1 · report
fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24 fa6e591e0ad2d888 · report
fixture: signature batch:list/1/Tensor · returned Tensor · level recorded 2026-09-24 census: 9 implementations from 11 papers, 8 distinct outputs across 4 buckets, one shared input per bucket core/utils.py ran fingerprinted MIT (permissive) ·
4f63545a8e689c49 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25 bd115aa43372ad6b · report
fixture: signature mu:ndarray/1/float, cov:ndarray/2/float, mu2:ndarray/1/float, cov2:ndarray/2/float · returned float64 · level recorded 2026-09-24 380e205f2b8ababc · report
fixture: signature start:int/0/int, end:int/0/int, step:float/0/float, len_tail:int/0/int · returned list · level recorded 2026-09-24 486935c1efc81482 · report
fixture: signature self:ScalarTensor/0/? · returned int · level recorded 2026-09-24 0dc6ba46b83190d8 · report
fixture: signature hm:Tensor/4/float · returned Tensor · level recorded 2026-09-25 cf9f3072be35c325 · report
fixture: signature n:int/0/int, in_f:int/0/int, out_f:int/0/int, kernel_size:NoneType/0/?, criterion:str/0/str · returned Tensor · level recorded 2026-09-24 346a1f46489131dd · report
fixture: signature torch_function:callable/0/? · returned function · level recorded 2026-09-24 d07d6906ac8b165a · report
fixture: signature dname:str/0/str · returned list · level recorded 2026-09-24 census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket core/wing.py ran fingerprinted MIT (permissive) ·
5cb99cf6b4b4728e · report
fixture: signature x:Tensor/4/float, eps:float/0/float · returned Tensor · level recorded 2026-09-24 census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket core/wing.py ran MIT (permissive) ·
73f22265368bbe0a · report
fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-24 fd27db1d1f4c93de · report
fixture: signature in_features:int/0/int, out_features:int/0/int, rng:RandomState/0/?, kernel_size:NoneType/0/?, criterion:str/0/str · returned tuple · level recorded 2026-09-24 a7e5a2da84b86174 · report
fixture: signature self:ScalarTensor/0/? · returned Size · level recorded 2026-09-24 census: 36 implementations from 56 papers, 7 distinct outputs across 3 buckets, one shared input per bucket core/utils.py ran fingerprinted MIT (permissive) ·
8b483042fac3893a · report
fixture: signature x:ndarray/1/float, w:float/0/float · returned ndarray · level recorded 2026-09-24 Tasks
Results from the paper archive 2025-07-28
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
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