Papers › GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data

GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data

11 Nov 2022arXiv:2211.06302archive 2025-07-28

Andrei Margeloiu, Nikola Simidjievski, Pietro Lio, Mateja Jamnik

Neural networks often struggle with high-dimensional but small sample-size tabular datasets. One reason is that current weight initialisation methods assume independence between weights, which can be problematic when there are insufficient samples to estimate the model's parameters accurately. In such small data scenarios, leveraging additional structures can improve the model's performance and training stability. To address this, we propose GCondNet, a general approach to enhance neural networks by leveraging implicit structures present in tabular data. We create a graph between samples for each data dimension, and utilise Graph Neural Networks (GNNs) to extract this implicit structure, and for conditioning the parameters of the first layer of an underlying predictor network. By creating many small graphs, GCondNet exploits the data's high-dimensionality, and thus improves the performance of an underlying predictor network. We demonstrate GCondNet's effectiveness on 12 real-world datasets, where it outperforms 14 standard and state-of-the-art methods. The results show that GCondNet is a versatile framework for injecting graph-regularisation into various types of neural networks, including MLPs and tabular Transformers. Code is available at https://github.com/andreimargeloiu/GCondNet.

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.

Syntology holds a reference implementation of GCondNet, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='GCondNet') (how to connect); the free check have('2211.06302') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 4 repositories linked to this paper: 13 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 7 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: 7 samples from 1 repository, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 13 samples from 3 repositories, 7 ran (3 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

andreimargeloiu/gcondnet officialmentioned in paperpytorchSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

20 samples harvested: 13 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
5ran
7unverified

Licence: 14 of the 20 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 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. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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”. For 1 sample 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. 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.

andreimargeloiu/gcondnet official repository 7 samples, 6 ran (0 instrument-failed) · 1 unverified
GNNWeightPredictorNetwork src/models.py ran no licence file found · pointer only · 42ddf24702948f06 · report fixture: returned GNNWeightPredictorNetwork · level recorded 2026-09-22
SparsityNetwork src/models.py ran fingerprinted no licence file found · pointer only · adfcee37607f04fd · report fixture: returned SparsityNetwork · level recorded 2026-09-22
WeightPredictorNetwork src/models.py ran no licence file found · pointer only · 6ba9ae7b6b50cd7e · report fixture: returned WeightPredictorNetwork · level recorded 2026-09-22
ZeroWeightPredictorNetwork src/models.py ran no licence file found · pointer only · 43e63844eb5d2d93 · report fixture: returned ZeroWeightPredictorNetwork · level recorded 2026-09-22
compute_graph_embeddings src/models.py ran · honoured contract no licence file found · pointer only · 6ff4ab3a68a7a9b5 · report fixture: signature gnn:callable/0/?, batch:callable/0/? · returned Tensor · level recorded 2026-09-22
linear_interpolation_coefficient src/models.py ran · honoured contract fingerprinted no licence file found · pointer only · 8b1858551f6b22c4 · report fixture: signature max_iterations:int/0/int, iteration:int/0/int · returned float · level recorded 2026-09-22
FirstLinearLayer src/models.py unverified no licence file found · pointer only · 9343413040a43530 · report
andreimargeloiu/WPFS found in paper text by Syntology 5 samples, 4 ran (2 instrument-failed) · 1 unverified
GeneralNeuralNetwork src/models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 87ab77b44f33747f · report fixture: returned GeneralNeuralNetwork · level recorded 2026-09-22
create_linear_layers src/models.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · 871a4aab89f8e63a · report fixture: signature args:Args/0/?, layer_sizes:list/1/int, layers_for_hidden_representation:int/0/int · returned tuple · level recorded 2026-09-22
get_labels_lists src/models.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract licence of this copy not recorded · cda491bdda02d633 · report fixture: signature outputs:list/1/dict · returned tuple · level recorded 2026-09-22
reshape_batch src/models.py ran · our draft was wrong no licence file found · pointer only · ff587bdefe78c65d · report fixture: signature batch:tuple/1/Tensor · returned tuple · level recorded 2026-09-22
detach_tensors src/models.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · ffdfda6bfc1ce5a8 · report
lasso-net/lassonet found in paper text by Syntology 6 samples, 3 ran (2 instrument-failed) · 3 unverified
prox lassonet/model.py ran · our draft was wrong MIT (permissive) · 375e015ef10a230a · report fixture: signature v:Tensor/1/float, u:Tensor/1/float, lambda_:float/0/float, lambda_bar:float/0/float, M:float/0/float · returned tuple · level recorded 2026-09-22
sign_binary lassonet/model.py ran · our draft was wrong fingerprinted MIT (permissive) · 72eb093eb143edd8 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
soft_threshold in 12 papers
census: 4 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
lassonet/model.py ran · honoured contract fingerprinted MIT (permissive) · 3f9208771cec0b61 · report fixture: signature l:float/0/float, x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
LassoNet lassonet/model.py unverified MIT (permissive) · a8a3e7989cfd2596 · report
inplace_group_prox lassonet/model.py unverified MIT (permissive) · dbb94584aa252f58 · report
inplace_prox lassonet/model.py unverified MIT (permissive) · 6c397ca47373e207 · report
jjfeng/spinn found in paper text by Syntology 2 samples, 0 ran · 2 unverified
NeuralNetwork in 7 papers neural_network.py unverified no licence file found · pointer only · 0e259c599f65cde2 · report
NeuralNetworkParams neural_network.py unverified no licence file found · pointer only · 69d8f664512ed227 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

4 assemblies on this paper: 3 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for GCondNet (graph method: GCondNet), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_mixed_weight_matrix entry · level 2 · ran · da729829e659c3c85733f8342513f8e99005f677164fbc85dee5a4931596b0bf

3 sibling assemblies for GCondNet (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for GCondNet (graph method: GCondNet). 5 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. GeneralNeuralNetwork entry · level 1 · ran · 87ab77b44f33747f
  2. create_linear_layers helper · level 1 · ran; the contract check could not run (RAISES) · 871a4aab89f8e63a
  3. detach_tensors helper · level 0 · unverified · ffdfda6bfc1ce5a8
  4. get_labels_lists helper · level 1 · ran · honoured contract · cda491bdda02d633
  5. reshape_batch helper · level 1 · ran · our draft was wrong · ff587bdefe78c65d

harvested Assembly for GCondNet (graph method: GCondNet). 7 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. FirstLinearLayer entry · level 0 · unverified · 9343413040a43530
  2. GNNWeightPredictorNetwork model · level 1 · ran · 42ddf24702948f06
  3. SparsityNetwork model · level 1 · ran · adfcee37607f04fd
  4. WeightPredictorNetwork model · level 1 · ran · 6ba9ae7b6b50cd7e
  5. ZeroWeightPredictorNetwork model · level 1 · ran · 43e63844eb5d2d93
  6. linear_interpolation_coefficient helper · level 1 · ran · honoured contract · 8b1858551f6b22c4
  7. compute_graph_embeddings helper · level 1 · ran · honoured contract · 6ff4ab3a68a7a9b5

harvested Assembly for GCondNet (graph method: GCondNet). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. NeuralNetwork entry · level 0 · unverified · 0e259c599f65cde2
  2. NeuralNetworkParams helper · level 0 · unverified · 69d8f664512ed227

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="2211.06302") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Vocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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