Papers › From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification

From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification

5 Feb 2016arXiv:1602.02068archive 2025-07-28

André F. T. Martins, Ramón Fernandez Astudillo

We propose sparsemax, a new activation function similar to the traditional softmax, but able to output sparse probabilities. After deriving its properties, we show how its Jacobian can be efficiently computed, enabling its use in a network trained with backpropagation. Then, we propose a new smooth and convex loss function which is the sparsemax analogue of the logistic loss. We reveal an unexpected connection between this new loss and the Huber classification loss. We obtain promising empirical results in multi-label classification problems and in attention-based neural networks for natural language inference. For the latter, we achieve a similar performance as the traditional softmax, but with a selective, more compact, attention focus.

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 4 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 4 repositories, 8 ran (6 with no instrument failure; 2 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 3 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.

AndreasMadsen/course-02456-sparsemax mentioned on GitHubtfSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
aced125/sparsemax mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ProtoAttend: Attention-Based Prototypical Learning (arXiv:1902.06292; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
deep-spin/entmax mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
dhruvdcoder/sparse-structured-attention mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
kriskorrel/sparsemax-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
qrfaction/keras-sparsemax mentioned on GitHubtfSyntology: not harvested report
vene/sparse-structured-attention mentioned on GitHubpytorchSyntology: not harvested report
weiwang2330/sparse-structured-attention mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
MindCode-4/code-12 mindsporeSyntology: not harvested report
MindCode-4/code-7 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to KPC-cF: Aspect-Based Sentiment Analysis via Implicit-Feature Alignment with Corpus Filtering (arXiv:2407.00342; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific-2/code-12 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks (arXiv:2506.05982; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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

8 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 2 violated, 0 with no contract checked; 2 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 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
2ran · violated contract
2ran · our draft was wrong

Licence: 2 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 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”. “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.

AndreasMadsen/course-02456-sparsemax community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Rop in 5 papers tensorflow_python/sparsemax.py ran · honoured contract fingerprinted MIT (permissive) · b95cf081a20568e0 · report fixture: signature z:ndarray/2/float, v:ndarray/2/float · returned ndarray · level recorded 2026-09-22
forward in 75 papers tensorflow_python/sparsemax.py ran · honoured contract fingerprinted MIT (permissive) · 8d31b8450757150f · report fixture: signature z:ndarray/2/float · returned ndarray · level recorded 2026-09-22
jacobian in 21 papers tensorflow_python/sparsemax.py ran · honoured contract MIT (permissive) · 6503187ed9b4502e · report fixture: signature z:ndarray/2/float · returned ndarray · level recorded 2026-09-22
deep-spin/entmax community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
entmax15 in 6 papers entmax/activations.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 · our draft was wrong fingerprinted licence of this copy not recorded · e41b90069aeca727 · report fixture: signature X:Tensor/2/float, dim:int/0/int, k:NoneType/0/?, return_support_size:bool/0/bool · returned Tensor · level recorded 2026-09-22
sparsemax in 11 papers entmax/activations.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 · our draft was wrong fingerprinted licence of this copy not recorded · df0db81c189b01e7 · report fixture: signature X:Tensor/2/float, dim:int/0/int, k:NoneType/0/?, return_support_size:bool/0/bool · returned Tensor · level recorded 2026-09-22
dhruvdcoder/sparse-structured-attention community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
project_simplex torchsparseattn/sparsemax.py ran · violated contract fingerprinted BSD-3-Clause (permissive) · 1f581f76688efd21 · report fixture: signature v:Tensor/2/float, z:float/0/float · returned Tensor · level recorded 2026-09-22
weiwang2330/sparse-structured-attention community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
project_simplex pytorch/torchsparseattn/sparsemax.py ran · violated contract fingerprinted BSD-3-Clause (permissive) · 3aead050bb96dbb8 · report fixture: signature v:Tensor/1/float, z:float/0/float · returned Tensor · level recorded 2026-09-22
sparsemax_grad pytorch/torchsparseattn/sparsemax.py ran · honoured contract fingerprinted BSD-3-Clause (permissive) · 4bc5ce61eaa1f3ee · report fixture: signature dout:Tensor/2/float, w_star:Tensor/2/float · returned Tensor · level recorded 2026-09-22

Tasks

General ClassificationMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationNatural Language Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Sparsemax

Sparsemax

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