Papers › A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship...

A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention

22 Jun 2020ICLR 2021 1arXiv:2006.12065archive 2025-07-28

Grégoire Mialon, Dexiong Chen, Alexandre d'Aspremont, Julien Mairal

We address the problem of learning on sets of features, motivated by the need of performing pooling operations in long biological sequences of varying sizes, with long-range dependencies, and possibly few labeled data. To address this challenging task, we introduce a parametrized representation of fixed size, which embeds and then aggregates elements from a given input set according to the optimal transport plan between the set and a trainable reference. Our approach scales to large datasets and allows end-to-end training of the reference, while also providing a simple unsupervised learning mechanism with small computational cost. Our aggregation technique admits two useful interpretations: it may be seen as a mechanism related to attention layers in neural networks, or it may be seen as a scalable surrogate of a classical optimal transport-based kernel. We experimentally demonstrate the effectiveness of our approach on biological sequences, achieving state-of-the-art results for protein fold recognition and detection of chromatin profiles tasks, and, as a proof of concept, we show promising results for processing natural language sequences. We provide an open-source implementation of our embedding that can be used alone or as a module in larger learning models at https://github.com/claying/OTK.

PaperPDFConference PDFCodeCode 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 13 code samples harvested from 1 repository linked to this paper: 5 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; 5 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 5 ran (0 with no instrument failure; 5 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

claying/OTK officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 5 ran (5 instrument-failed) · 8 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

13 samples harvested: 5 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; 5 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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.

1ran · our draft was wrong
4ran; the contract check could not run
8unverified

Licence: 13 of the 13 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 claying/OTK. “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. 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.

claying/OTK official repository 13 samples, 5 ran (5 instrument-failed) · 8 unverified
log_sinkhorn in 7 papers otk/layers.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 6a5b264a00dc40db · report fixture: signature K:Tensor/3/float, mask:Tensor/2/bool, eps:float/0/float, return_kernel:bool/0/bool, max_iter:int/0/int · returned Tensor · level recorded 2026-09-22
multihead_attn otk/layers.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 0ad8efb4913866f6 · report fixture: signature input:Tensor/3/float, weight:Tensor/3/float, mask:Tensor/2/bool, eps:float/0/float, return_kernel:bool/0/bool, max_iter:int/0/int, log_domain:bool/0/bool, position_filter:Tensor/4/float · returned Tensor · level recorded 2026-09-22
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket this sample: bucket 1 of 11, arg 1: rank 2, kind float, dtype float32
otk/layers.py ran · our draft was wrong fingerprinted no licence file found · pointer only · ea90720465da3345 · report fixture: signature x:Tensor/2/float, p:int/0/int, dim:int/0/int, inplace:bool/0/bool · returned Tensor · level recorded 2026-09-22
sinkhorn in 47 papers
census: 11 implementations from 11 papers, 11 distinct outputs across 2 buckets, one shared input per bucket
otk/layers.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 55a8cdfd0f911b6a · report fixture: signature dot:Tensor/3/float, mask:Tensor/2/float, eps:float/0/float, return_kernel:bool/0/bool, max_iter:int/0/int · returned Tensor · level recorded 2026-09-22
spherical_kmeans otk/layers.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 838829b61cf82bd2 · report fixture: signature x:Tensor/3/float, n_clusters:int/0/int, max_iters:int/0/int, block_size:int/0/int, verbose:bool/0/bool, init:NoneType/0/?, eps:float/0/float · returned Tensor · level recorded 2026-09-22
OTKernel otk/layers.py unverified no licence file found · pointer only · 8713f1365af9fd76 · report
OTKernel otk/layers.py unverified no licence file found · pointer only · c195abdcd448e5a0 · report
multihead_attn otk/layers.py unverified no licence file found · pointer only · 210485a16a60a08e · report
spherical_kmeans otk/layers.py unverified no licence file found · pointer only · fb854c01aaabc359 · report
wasserstein_barycenter otk/layers.py unverified no licence file found · pointer only · c6f00e8b22fa76ed · report
wasserstein_kmeans otk/layers.py unverified no licence file found · pointer only · a95baa30738e561e · report
wasserstein_kmeans otk/layers.py unverified no licence file found · pointer only · 2e43b81b2901488c · 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 TRAINABLE OPTIMAL TRANSPORT EMBEDDING (graph method: TRAINABLE OPTIMAL TRANSPORT EMBEDDING). 8 bricks; individually on a fixture: 5 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; 5 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. OTKernel entry · level 0 · unverified · c195abdcd448e5a0
  2. multihead_attn helper · level 1 · ran; the contract check could not run (RAISES) · 0ad8efb4913866f6
  3. normalize helper · level 1 · ran · our draft was wrong · ea90720465da3345
  4. wasserstein_kmeans helper · level 0 · unverified · 2e43b81b2901488c
  5. log_sinkhorn helper · level 1 · ran; the contract check could not run (RAISES) · 6a5b264a00dc40db
  6. sinkhorn helper · level 1 · ran; the contract check could not run (RAISES) · 55a8cdfd0f911b6a
  7. spherical_kmeans helper · level 1 · ran; the contract check could not run (RAISES) · 838829b61cf82bd2
  8. wasserstein_barycenter helper · level 0 · unverified · c6f00e8b22fa76ed

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="2006.12065") 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.

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