SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.02631 · ICLR · 2022

RotoGrad: Gradient Homogenization in Multitask Learning

Isabel Valera, Adrián Javaloy

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2103.02631.json · badge: /api/ran/2103.02631.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
adrianjav/rotograd canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
divide Ran
ran; our contract draft was wrong, not the code
adrianjav/rotograd/rotograd/rotograd.py
pointer only (licence: NONE) · get_code("3f26bd1327c42c88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adrianjav/rotograd 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.

rotate Ran
ran; our contract draft was wrong, not the code
adrianjav/rotograd/rotograd/rotograd.py
pointer only (licence: NONE) · get_code("0c481cf52720ca1e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adrianjav/rotograd 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.

rotate_back Ran
ran; our contract draft was wrong, not the code
adrianjav/rotograd/rotograd/rotograd.py
pointer only (licence: NONE) · get_code("c7a2edbc4d030bf0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, adrianjav/rotograd 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.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 2 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
divide 1 other paper
1 later
2206.04496 (2022-06)
Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization

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

Multitask learning is being increasingly adopted in applications domains like computer vision and reinforcement learning. However, optimally exploiting its advantages remains a major challenge due to the effect of negative transfer. Previous works have tracked down this issue to the disparities in gradient magnitudes and directions across tasks when optimizing the shared network parameters. While recent work has acknowledged that negative transfer is a two-fold problem, existing approaches fall short. These methods only focus on either homogenizing the gradient magnitude across tasks; or greedily change the gradient directions, overlooking future conflicts. In this work, we introduce RotoGrad, an algorithm that tackles negative transfer as a whole: it jointly homogenizes gradient magnitudes and directions, while ensuring training convergence. We show that RotoGrad outperforms competing methods in complex problems, including multi-label classification in CelebA and computer vision tasks in the NYUv2 dataset. A Pytorch implementation can be found in https://github.com/adrianjav/rotograd.

For agents

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

get_harvested_code_for_paper("2103.02631")
get_code_for_paper("2103.02631")
have("2103.02631")

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

curl https://syntology.ai/api/ran/2103.02631.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.02631.svg)](https://syntology.ai/paper/2103.02631)

Connect an agent — have() is free.