SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.04522 · NeurIPS · 2021

Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

Erik Englesson, Hossein Azizpour

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2105.04522.json · badge: /api/ran/2105.04522.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
erikenglesson/gjs canonical (classifier label)
classifier basis: classifier_2025
4 ran · 1 no recorded run
FunctionStatusWhere it lives
JensenShannonDivergenceWeightedCustom Ran
ran on a synthesized input · constructed an object; no result was computed
erikenglesson/gjs/losses.py
pointer only (licence: NONE) · get_code("411608e7efd42f94")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, erikenglesson/gjs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

custom_ce Ran
ran; our contract draft was wrong, not the code
erikenglesson/gjs/losses.py
pointer only (licence: NONE) · get_code("f07ad940a29ae3c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, erikenglesson/gjs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

custom_kl_div Ran
ran; our contract draft was wrong, not the code
erikenglesson/gjs/losses.py
pointer only (licence: NONE) · get_code("b7e66a91c19383df")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, erikenglesson/gjs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

custom_kl_div Ran
ran, honoured the contract we drafted
erikenglesson/gjs/losses.py
pointer only (licence: NONE) · get_code("f508a1f840aee873")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, erikenglesson/gjs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_criterion Not yet run
unverified (harvested, no recorded run)
erikenglesson/gjs/losses.py
pointer only (licence: NONE) · get_code("c5746d47232aa0b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, erikenglesson/gjs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
custom_kl_div
brick of this paper's assembly: helper
2 other papers
2 later
2112.14869 (2021-12)
Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity
2206.02659 (2022-06)
Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Prior works have found it beneficial to combine provably noise-robust loss functions e.g., mean absolute error (MAE) with standard categorical loss function e.g. cross entropy (CE) to improve their learnability. Here, we propose to use Jensen-Shannon divergence as a noise-robust loss function and show that it interestingly interpolate between CE and MAE with a controllable mixing parameter. Furthermore, we make a crucial observation that CE exhibits lower consistency around noisy data points. Based on this observation, we adopt a generalized version of the Jensen-Shannon divergence for multiple distributions to encourage consistency around data points. Using this loss function, we show state-of-the-art results on both synthetic (CIFAR), and real-world (e.g. WebVision) noise with varying noise rates.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2105.04522")
get_code_for_paper("2105.04522")
have("2105.04522")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2105.04522.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2105.04522.svg)](https://syntology.ai/paper/2105.04522)

Connect an agent — have() is free.