SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.05082 · ICML · 2024

DMTG: One-Shot Differentiable Multi-Task Grouping

Yuan Gao, Gui-Song Xia, Jin-Gang Yu, Shuguo Jiang, Moran Li

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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; 5 failures of our instrument; 2 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/2407.05082.json · badge: /api/ran/2407.05082.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
ethanygao/DMTG canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
ethanygao/dmtg canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
LearnToGroup Ran
ran on a synthesized input · constructed an object; no result was computed
ethanygao/dmtg/models/learnToGroup.py
pointer only (licence: NONE) · get_code("2e42e0959bdc24e7")
How it ran

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

confusion_matrix Ran
ran, honoured the contract we drafted
ethanygao/DMTG/utils/model_utils.py
pointer only (licence: NONE) · get_code("0abd470ee2dbde8d")
How it ran

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

normal_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ethanygao/DMTG/models/loss.py
pointer only (licence: NONE) · get_code("cd730753ce887a0b")
How it ran

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

normal_loss_simple Ran
ran; our contract draft was wrong, not the code
ethanygao/DMTG/models/loss.py
pointer only (licence: NONE) · get_code("93828fef55cb0392")
How it ran

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

register Ran
ran; our contract draft was wrong, not the code
ethanygao/DMTG/models/models.py
pointer only (licence: NONE); the stored copy get_code serves, from liyuantsao/flowsr-lp, is pointer only (licence: NONE) · get_code("44c3aa4c610ea3f7")
How it ran

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

segment_semantic_loss Ran
ran; our contract draft was wrong, not the code
ethanygao/DMTG/models/loss.py
pointer only (licence: NONE) · get_code("b899239fa359c4d4")
How it ran

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

time_text Ran
ran; our contract draft was wrong, not the code
ethanygao/DMTG/utils/model_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from ai-spatial/GeoSR-Bench, is pointer only (licence: NONE) · get_code("14982a5b13861f94")
How it ran

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

gradient_normalizers Not yet run
unverified (harvested, no recorded run)
ethanygao/DMTG/models/ozan_min_norm_solvers.py
pointer only (licence: NONE); the stored copy get_code serves, from lisha-chen/ferero, is pointer only (licence: NONE) · get_code("fe93d608f889f824")
How it ran

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

make Not yet run
unverified (harvested, no recorded run)
ethanygao/DMTG/models/models.py
pointer only (licence: NONE) · get_code("9e49a3839a22867f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ethanygao/DMTG 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 3 later) and 6 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
register 24 other papers
14 dated earlier, 1 the same month, 8 later, 1 same year, order not determinable · 9 only as an assembly brick
2003.04390 (2020-03)
Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning
2010.00763 (2020-10)
BONGARD-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
2111.00195 (2021-11)
Learning Continuous Representation of Audio for Arbitrary Scale Super Resolution
and 21 more not named here
time_text 8 other papers
5 dated earlier, 3 later
2108.11084 (2021-08)
Transformer for Single Image Super-Resolution
2111.08918 (2021-11)
Local Texture Estimator for Implicit Representation Function
and 5 more not named here
gradient_normalizers 3 other papers
1 dated earlier, 2 later
1912.12854 (2019-12)
Pareto Multi-Task Learning
2412.01773 (2024-12)
FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning
aaai_33460 (2025 (year only))
Neighborhood-Aware Negative Sampling for Student Knowledge and Behavior Modeling

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

We aim to address Multi-Task Learning (MTL) with a large number of tasks by Multi-Task Grouping (MTG). Given N tasks, we propose to simultaneously identify the best task groups from 2 N candidates and train the model weights simultaneously in one-shot, with the high-order taskaffinity fully exploited. This is distinct from the pioneering methods which sequentially identify the groups and train the model weights, where the group identification often relies on heuristics. As a result, our method not only improves the training efficiency, but also mitigates the objective bias introduced by the sequential procedures that potentially lead to a suboptimal solution. Specifically, we formulate MTG as a fully differentiable pruning problem on an adaptive network architecture determined by an underlying Categorical distribution. To categorize N tasks into K groups (represented by K encoder branches), we initially set up KN task heads, where each branch connects to all N task heads to exploit the high-order taskaffinity. Then, we gradually prune the KN heads down to N by learning a relaxed differentiable Categorical distribution, ensuring that each task is exclusively and uniquely categorized into only one branch. Extensive experiments on CelebA and Taskonomy datasets with detailed ablations show the promising performance and efficiency of our method. The codes are available at https://github.com/ethanygao/DMTG.

For agents

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

get_harvested_code_for_paper("2407.05082")
get_code_for_paper("2407.05082")
have("2407.05082")

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

curl https://syntology.ai/api/ran/2407.05082.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.05082.svg)](https://syntology.ai/paper/2407.05082)

Connect an agent — have() is free.