Papers › Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification

Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification

16 Oct 2023arXiv:2310.10443archive 2025-07-28

Andreas Grivas, Antonio Vergari, Adam Lopez

Sigmoid output layers are widely used in multi-label classification (MLC) tasks, in which multiple labels can be assigned to any input. In many practical MLC tasks, the number of possible labels is in the thousands, often exceeding the number of input features and resulting in a low-rank output layer. In multi-class classification, it is known that such a low-rank output layer is a bottleneck that can result in unargmaxable classes: classes which cannot be predicted for any input. In this paper, we show that for MLC tasks, the analogous sigmoid bottleneck results in exponentially many unargmaxable label combinations. We explain how to detect these unargmaxable outputs and demonstrate their presence in three widely used MLC datasets. We then show that they can be prevented in practice by introducing a Discrete Fourier Transform (DFT) output layer, which guarantees that all sparse label combinations with up to k active labels are argmaxable. Our DFT layer trains faster and is more parameter efficient, matching the F1@k score of a sigmoid layer while using up to 50% fewer trainable parameters. Our code is publicly available at https://github.com/andreasgrv/sigmoid-bottleneck.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2310.10443")

Code

Syntology Ran 13 of 14 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 13 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

andreasgrv/sigmoid-bottleneck officialmentioned in papermentioned on GitHubpytorchMIT 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

14 samples harvested; 13 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

13ran
1unverified

Licence: 0 of the 14 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 andreasgrv/sigmoid-bottleneck. “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.

affinise andreasgrv/sigmoid-bottleneck/spmlbl/modules.py official repository ran fingerprinted MIT (permissive) · aa97babdb6f4b212 · report
count_alternating_bits andreasgrv/sigmoid-bottleneck/spmlbl/verify.py official repository ran fingerprinted MIT (permissive) · 467640b6cac88182 · report
cyclic_polytope_trig andreasgrv/sigmoid-bottleneck/spmlbl/modules.py official repository ran fingerprinted MIT (permissive) · 95a1b13f612e6900 · report
encode_batch_labels andreasgrv/sigmoid-bottleneck/spmlbl/data.py official repository ran MIT (permissive) · f1080c6e6756f465 · report
encode_label_list andreasgrv/sigmoid-bottleneck/spmlbl/data.py official repository ran MIT (permissive) · 83ded52943d23cf3 · report
f1 andreasgrv/sigmoid-bottleneck/spmlbl/metrics.py official repository ran MIT (permissive) · 77bf2eea0dac3863 · report
f1_counts andreasgrv/sigmoid-bottleneck/spmlbl/metrics.py official repository ran MIT (permissive) · 09b29a8958f3dcca · report
generate_card_samples andreasgrv/sigmoid-bottleneck/plots/argmaxability_slack/check_infeasible_cyclic.py official repository ran MIT (permissive) · f072f1c9d0e306c2 · report
k_hot_to_dense andreasgrv/sigmoid-bottleneck/spmlbl/verify.py official repository ran MIT (permissive) · 9da5519e0206563b · report
linear_dependence andreasgrv/sigmoid-bottleneck/spmlbl/math.py official repository ran fingerprinted MIT (permissive) · 50a7ff0312b87b82 · report
orthogonal_complement andreasgrv/sigmoid-bottleneck/spmlbl/math.py official repository ran fingerprinted MIT (permissive) · 43e11696974c4c73 · report
pattern_is_feasible_cyclic andreasgrv/sigmoid-bottleneck/spmlbl/verify.py official repository ran MIT (permissive) · a51b6a4a498e44a8 · report
torch_interleave_columns andreasgrv/sigmoid-bottleneck/spmlbl/modules.py official repository ran fingerprinted MIT (permissive) · e29b1f502ab0b31f · report
encode_bpe_label_list andreasgrv/sigmoid-bottleneck/spmlbl/data.py official repository unverified MIT (permissive) · b1095adb35aeb739 · report

Tasks

MUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationMulti-class Classification

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