Papers › Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data

Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data

3 Sep 2024arXiv:2409.01832archive 2025-07-28

Wanli Hong, Shuyang Ling

Neural collapse (NC) is a phenomenon that emerges at the terminal phase of the training (TPT) of deep neural networks (DNNs). The features of the data in the same class collapse to their respective sample means and the sample means exhibit a simplex equiangular tight frame (ETF). In the past few years, there has been a surge of works that focus on explaining why the NC occurs and how it affects generalization. Since the DNNs are notoriously difficult to analyze, most works mainly focus on the unconstrained feature model (UFM). While the UFM explains the NC to some extent, it fails to provide a complete picture of how the network architecture and the dataset affect NC. In this work, we focus on shallow ReLU neural networks and try to understand how the width, depth, data dimension, and statistical property of the training dataset influence the neural collapse. We provide a complete characterization of when the NC occurs for two or three-layer neural networks. For two-layer ReLU neural networks, a sufficient condition on when the global minimizer of the regularized empirical risk function exhibits the NC configuration depends on the data dimension, sample size, and the signal-to-noise ratio in the data instead of the network width. For three-layer neural networks, we show that the NC occurs as long as the first layer is sufficiently wide. Regarding the connection between NC and generalization, we show the generalization heavily depends on the SNR (signal-to-noise ratio) in the data: even if the NC occurs, the generalization can still be bad provided that the SNR in the data is too low. Our results significantly extend the state-of-the-art theoretical analysis of the N C under the UFM by characterizing the emergence of the N C under shallow nonlinear networks and showing how it depends on data properties and network architecture.

PaperPDFCodeCode Syntology ran

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 8 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 8 ran (4 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

wanlihongc/neural-collapse officialpytorchSyntology: 8 samples, 8 ran (4 instrument-failed) · 0 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

8 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 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.

1ran · honoured contract
4ran · our draft was wrong
3ran

Licence: 8 of the 8 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 wanlihongc/neural-collapse. “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.

wanlihongc/neural-collapse official repository 8 samples, 8 ran (4 instrument-failed) · 0 unverified
ResNet18 in 174 papers train_utils.py ran · our draft was wrong no licence file found · pointer only · d660ed438cb5aa30 · report fixture: signature color_channel:int/0/int, num_classes:int/0/int · returned ResNet · level recorded 2026-09-24
ResNet18_bf train_utils.py ran · our draft was wrong no licence file found · pointer only · 0094dfa7ee8ad011 · report fixture: signature color_channel:int/0/int, num_classes:int/0/int · returned ResNet_bf · level recorded 2026-09-24
ResNet34 in 91 papers train_utils.py ran · our draft was wrong no licence file found · pointer only · 79c1cacca9bb2e2d · report fixture: signature color_channel:int/0/int, num_classes:int/0/int · returned ResNet · level recorded 2026-09-24
compute_pairwise_angle ana_utils.py ran · honoured contract fingerprinted no licence file found · pointer only · ca975b12a28b5260 · report fixture: signature F:ndarray/2/float · returned ndarray · level recorded 2026-09-24
get_minibatches_idx utils.py ran no licence file found · pointer only · e44fdd6f7b716e4d · report fixture: signature n:int/0/int, minibatch_size:int/0/int, shuffle:bool/0/bool · returned list · level recorded 2026-09-24
get_weighted_minibatches_idx utils.py ran no licence file found · pointer only · 8ab001dc7e871ae3 · report fixture: signature n:int/0/int, minibatch_size:int/0/int, weighted_idx:ndarray/1/int, ratio:float/0/float, shuffle:bool/0/bool · returned list · level recorded 2026-09-24
load_data_from_pickle utils.py ran · our draft was wrong no licence file found · pointer only · b5eb1a41b8181c5c · report fixture: signature name:str/0/str · returned list · level recorded 2026-09-24
solve_cvx ana_utils.py ran no licence file found · pointer only · dc9a3ff84723e3bc · report fixture: signature n_list:list/1/int, l:float/0/float, l_2:float/0/float, K:int/0/int · returned tuple · level recorded 2026-09-24

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

FocusReLU

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