Papers › Monomial Matrix Group Equivariant Neural Functional Networks

Monomial Matrix Group Equivariant Neural Functional Networks

18 Sep 2024arXiv:2409.11697archive 2025-07-28

Hoang V. Tran, Thieu N. Vo, Tho H. Tran, An T. Nguyen, Tan M. Nguyen

Neural functional networks (NFNs) have recently gained significant attention due to their diverse applications, ranging from predicting network generalization and network editing to classifying implicit neural representation. Previous NFN designs often depend on permutation symmetries in neural networks' weights, which traditionally arise from the unordered arrangement of neurons in hidden layers. However, these designs do not take into account the weight scaling symmetries of ReLU networks, and the weight sign flipping symmetries of sin or Tanh networks. In this paper, we extend the study of the group action on the network weights from the group of permutation matrices to the group of monomial matrices by incorporating scaling/sign-flipping symmetries. Particularly, we encode these scaling/sign-flipping symmetries by designing our corresponding equivariant and invariant layers. We name our new family of NFNs the Monomial Matrix Group Equivariant Neural Functional Networks (Monomial-NFN). Because of the expansion of the symmetries, Monomial-NFN has much fewer independent trainable parameters compared to the baseline NFNs in the literature, thus enhancing the model's efficiency. Moreover, for fully connected and convolutional neural networks, we theoretically prove that all groups that leave these networks invariant while acting on their weight spaces are some subgroups of the monomial matrix group. We provide empirical evidence to demonstrate the advantages of our model over existing baselines, achieving competitive performance and efficiency.

PaperPDFCodeCode Syntology ranMethod as code

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):

Code

Syntology 36 code samples harvested from 1 repository linked to this paper: 26 ran (of which 14 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 9 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 36 samples from 1 repository, 26 ran (17 with no instrument failure; 9 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 26 samples that ran have no recorded date.

mathematicalai-nus/monomial-nfn officialmentioned in paperpytorchMITSyntology: 36 samples, 26 ran (9 instrument-failed) · 10 unverified 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

36 samples harvested: 26 ran (of which 14 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 9 where Syntology's instrument failed) · 10 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.

9ran · our draft was wrong
17ran
10unverified

Licence: 0 of the 36 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 mathematicalai-nus/monomial-nfn. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

mathematicalai-nus/monomial-nfn official repository 36 samples, 26 ran (9 instrument-failed) · 10 unverified
ArraySpec experiments/models.py ran · metamorphic tier: deterministic MIT (permissive) · 8178c2d555c68f4b · report fixture: returned ArraySpec · level recorded 2026-09-22
ChannelDropout experiments/models.py ran · metamorphic tier: deterministic MIT (permissive) · ca1d055a4db1e6d9 · report fixture: returned ChannelDropout · level recorded 2026-09-22
ChannelLayerNorm experiments/models.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · a878a9a8b0f2ab3e · report fixture: returned ChannelLayerNorm · level recorded 2026-09-22
ChannelLinear experiments/models.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 40353a86c31fca90 · report fixture: returned ChannelLinear · level recorded 2026-09-22
EinsumLayer experiments/models.py ran · metamorphic tier: deterministic MIT (permissive) · c2e173b5a7b62641 · report fixture: returned EinsumLayer · level recorded 2026-09-22
GaussianFourierFeatureTransform experiments/models.py ran · metamorphic tier: deterministic MIT (permissive) · 48fe3dea36f9c89e · report fixture: returned GaussianFourierFeatureTransform · level recorded 2026-09-22
IOSinusoidalEncoding experiments/models.py ran · metamorphic tier: deterministic MIT (permissive) · 26be31658f5e058b · report fixture: returned IOSinusoidalEncoding · level recorded 2026-09-22
NetworkSpec experiments/models.py ran · metamorphic tier: deterministic MIT (permissive) · 470213dfc5111c7e · report fixture: returned NetworkSpec · level recorded 2026-09-22
NormalizingModule experiments/models.py ran · metamorphic tier: deterministic MIT (permissive) · 1db75947d6ce1f3b · report fixture: returned NormalizingModule · level recorded 2026-09-22
ParamLayerNorm experiments/models.py ran · metamorphic tier: deterministic MIT (permissive) · dddb1bf40099aca9 · report fixture: returned ParamLayerNorm · level recorded 2026-09-22
Pointwise experiments/models.py ran · metamorphic tier: deterministic MIT (permissive) · f6a29acf17a126b8 · report fixture: returned Pointwise · level recorded 2026-09-22
SimpleLayerNorm experiments/models.py ran · metamorphic tier: deterministic MIT (permissive) · 0b69c6dba62cba08 · report fixture: returned SimpleLayerNorm · level recorded 2026-09-22
TupleOp experiments/models.py ran · metamorphic tier: deterministic MIT (permissive) · ce83a7db6de57bec · report fixture: returned TupleOp · level recorded 2026-09-22
WeightSpaceFeatures experiments/models.py ran MIT (permissive) · 13dc87e6610b8b4e · report fixture: returned WeightSpaceFeatures · level recorded 2026-09-22
compute_mean_std in 20 papers experiments/data_utils.py ran · our draft was wrong MIT (permissive) · 9870adcdf1003523 · report fixture: signature loader:list/1/tuple, max_batches:int/0/int · returned tuple · level recorded 2026-09-24
fourier_encode in 5 papers nfn/layers/encoding.py ran · our draft was wrong MIT (permissive) · 260b648862af987e · report fixture: signature x:Tensor/2/float, max_freq:float/0/float, num_bands:int/0/int · returned Tensor · level recorded, date not recorded
fourier_encode in 5 papers experiments/models.py ran · our draft was wrong MIT (permissive) · 5febbdfeec3c83ff · report fixture: signature x:Tensor/2/float, max_freq:float/0/float, num_bands:int/0/int · returned Tensor · level recorded 2026-09-22
get_npy_from_state_dict experiments/data_utils.py ran · our draft was wrong MIT (permissive) · b6b09a11976ae372 · report fixture: signature state_dict:dict/0/? · returned tuple · level recorded 2026-09-24
get_state_dict_from_npy experiments/data_utils.py ran MIT (permissive) · 6b2124e8e2fb9a33 · report fixture: signature cnn:callable/0/?, weight:list/1/ndarray, bias:list/1/ndarray · returned OrderedDict · level recorded 2026-09-24
params_to_state_dicts nfn/common/data.py ran MIT (permissive) · ef49a788da8dde77 · report fixture: signature keys:list/1/str, wsfeat:WeightSpaceFeatures/0/? · returned list · level recorded 2026-09-24
shape_wsfeat_symmetry experiments/models.py ran · our draft was wrong MIT (permissive) · c0a8a100ad21973a · report fixture: signature params:WeightSpaceFeatures/0/?, network_spec:NetworkSpec/0/? · returned WeightSpaceFeatures · level recorded 2026-09-22
simple_attention experiments/models.py ran · our draft was wrong MIT (permissive) · 1fd171846ef2ef36 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, dropout:callable/0/? · returned Tensor · level recorded 2026-09-22
simple_attention nfn/layers/layers.py ran MIT (permissive) · dafd3ba91930d52f · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, dropout:callable/0/? · returned Tensor · level recorded 2026-09-24
state_dict_to_tensors nfn/common/data.py ran · our draft was wrong MIT (permissive) · d127d7b6cd98eaf2 · report fixture: signature state_dict:dict/0/? · returned tuple · level recorded 2026-09-24
train_step in 47 papers experiments/classify_siren.py ran · our draft was wrong MIT (permissive) · baf32f15bff306f8 · report fixture: returned tuple · level recorded, date not recorded
unshape_wsfeat_symmetry experiments/models.py ran · our draft was wrong MIT (permissive) · 9fb54e896d3ed074 · report fixture: signature params:WeightSpaceFeatures/0/?, network_spec:NetworkSpec/0/? · returned WeightSpaceFeatures · level recorded 2026-09-22
HNPLinear experiments/models.py unverified MIT (permissive) · 29a32995bc174d5a · report
HNPSLinear experiments/models.py unverified MIT (permissive) · c121ad9422f9a2f9 · report
HNPS_SirenLinear experiments/models.py unverified MIT (permissive) · 5ba93c4071e28b32 · report
InvariantNFN_HNPS experiments/models.py unverified MIT (permissive) · 3cf245773e40b81d · report
NPAttention experiments/models.py unverified MIT (permissive) · 247366d488114b00 · report
NPLinear experiments/models.py unverified MIT (permissive) · 32c44311b1642ecb · report
StatFeaturizer experiments/models.py unverified MIT (permissive) · e868a1e2f9647f67 · report
network_spec_from_wsfeat nfn/common/data.py unverified MIT (permissive) · bb77e575f8866574 · report
set_init_ experiments/models.py unverified MIT (permissive) · 3e3e39920e776702 · report
set_init_einsum_ experiments/models.py unverified MIT (permissive) · 8433cbb2dd1ac57c · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Monomial Matrix Group Equivariant Neural Functional Networks (graph method: Monomial Matrix Group Equivariant Neural Functional Networks). 27 bricks; individually on a fixture: 18 ran (of which 14 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. InvariantNFN_HNPS entry · level 0 · unverified · 3cf245773e40b81d
  2. ChannelDropout helper · level 1 · ran · ca1d055a4db1e6d9
  3. HNPSLinear model · level 0 · unverified · c121ad9422f9a2f9
  4. HNPS_SirenLinear helper · level 0 · unverified · 5ba93c4071e28b32
  5. IOSinusoidalEncoding helper · level 1 · ran · 26be31658f5e058b
  6. NetworkSpec helper · level 1 · ran · 470213dfc5111c7e
  7. NormalizingModule data_transform · level 1 · ran · 1db75947d6ce1f3b
  8. StatFeaturizer helper · level 0 · unverified · e868a1e2f9647f67
  9. TupleOp helper · level 1 · ran · ce83a7db6de57bec
  10. WeightSpaceFeatures helper · level 1 · ran · 13dc87e6610b8b4e
  11. EinsumLayer helper · level 1 · ran · c2e173b5a7b62641
  12. set_init_einsum_ helper · level 0 · unverified · 8433cbb2dd1ac57c
  13. shape_wsfeat_symmetry helper · level 1 · ran · our draft was wrong · c0a8a100ad21973a
  14. unshape_wsfeat_symmetry helper · level 1 · ran · our draft was wrong · 9fb54e896d3ed074
  15. fourier_encode helper · level 1 · ran · our draft was wrong · 5febbdfeec3c83ff
  16. ArraySpec helper · level 1 · ran · 8178c2d555c68f4b
  17. ChannelLayerNorm helper · level 1 · ran · a878a9a8b0f2ab3e
  18. ChannelLinear helper · level 1 · ran · 40353a86c31fca90
  19. GaussianFourierFeatureTransform helper · level 1 · ran · 48fe3dea36f9c89e
  20. set_init_ helper · level 0 · unverified · 3e3e39920e776702
  21. simple_attention helper · level 1 · ran · our draft was wrong · 1fd171846ef2ef36
  22. HNPLinear helper · level 0 · unverified · 29a32995bc174d5a
  23. NPAttention helper · level 0 · unverified · 247366d488114b00
  24. NPLinear helper · level 0 · unverified · 32c44311b1642ecb
  25. ParamLayerNorm helper · level 1 · ran · dddb1bf40099aca9
  26. Pointwise helper · level 1 · ran · f6a29acf17a126b8
  27. SimpleLayerNorm helper · level 1 · ran · 0b69c6dba62cba08

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2409.11697") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionNFNSoftmax

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