Papers › Selective Task Group Updates for Multi-Task Optimization

Selective Task Group Updates for Multi-Task Optimization

17 Feb 2025arXiv:2502.11986archive 2025-07-28

Wooseong Jeong, Kuk-Jin Yoon

Multi-task learning enables the acquisition of task-generic knowledge by training multiple tasks within a unified architecture. However, training all tasks together in a single architecture can lead to performance degradation, known as negative transfer, which is a main concern in multi-task learning. Previous works have addressed this issue by optimizing the multi-task network through gradient manipulation or weighted loss adjustments. However, their optimization strategy focuses on addressing task imbalance in shared parameters, neglecting the learning of task-specific parameters. As a result, they show limitations in mitigating negative transfer, since the learning of shared space and task-specific information influences each other during optimization. To address this, we propose a different approach to enhance multi-task performance by selectively grouping tasks and updating them for each batch during optimization. We introduce an algorithm that adaptively determines how to effectively group tasks and update them during the learning process. To track inter-task relations and optimize multi-task networks simultaneously, we propose proximal inter-task affinity, which can be measured during the optimization process. We provide a theoretical analysis on how dividing tasks into multiple groups and updating them sequentially significantly affects multi-task performance by enhancing the learning of task-specific parameters. Our methods substantially outperform previous multi-task optimization approaches and are scalable to different architectures and various numbers of tasks.

PaperPDFCodeCode 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.

Syntology holds a reference implementation of SELECTIVE TASK GROUP UPDATES, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='SELECTIVE TASK GROUP UPDATES') (how to connect); the free check have('2502.11986') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 6 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 6 ran (3 with no instrument failure; 3 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.

wooseong97/sel-update-mtl officialmentioned on GitHubpytorchSyntology: 16 samples, 6 ran (3 instrument-failed) · 10 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

16 samples harvested: 6 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 10 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.

1ran · violated contract
3ran; the contract check could not run
2ran
10unverified

Licence: 0 of the 16 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 wooseong97/sel-update-mtl. “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.

wooseong97/sel-update-mtl official repository 16 samples, 6 ran (3 instrument-failed) · 10 unverified
MetricLogger sel-update-mtl/utils/train_utils.py ran MIT (permissive) · f5627726b4ae2bcc · report fixture: returned MetricLogger · level recorded 2026-09-22
SmoothedValue sel-update-mtl/utils/train_utils.py ran MIT (permissive) · 79d5ce6f2d2f4574 · report fixture: returned SmoothedValue · level recorded 2026-09-22
get_loss in 107 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
sel-update-mtl/utils/train_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 32835f4d0f551b1b · report fixture: signature outputs:Tensor/2/float, targets:Tensor/2/float, task:str/0/str · returned Tensor · level recorded 2026-09-22
get_metric in 19 papers sel-update-mtl/utils/train_utils.py ran · violated contract fingerprinted MIT (permissive) · 4799ae2084413fda · report fixture: signature outputs:Tensor/2/float, targets:Tensor/2/float, task:str/0/str · returned float · level recorded 2026-09-22
get_output in 19 papers sel-update-mtl/utils/train_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · a64ab65acb301c2d · report fixture: signature output:Tensor/4/float, task:str/0/str · returned Tensor · level recorded 2026-09-22
to_cuda in 51 papers
census: 8 implementations from 8 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
sel-update-mtl/utils/train_utils.py ran; the contract check could not run (RAISES) MIT (permissive) · 48fca14a672a5108 · report fixture: returned dict · level recorded 2026-09-22
PerformanceMeter sel-update-mtl/utils/train_utils.py unverified MIT (permissive) · 05242b3a981049cf · report
evaluate in 514 papers sel-update-mtl/utils/train_utils.py unverified MIT (permissive) · cc95be4bcb3a1abd · report
get_single_task_meter sel-update-mtl/utils/train_utils.py unverified MIT (permissive) · 6a216e80da829b4d · report
mkdir_if_missing sel-update-mtl/utils/train_utils.py unverified MIT (permissive) · 3cc281449dc70540 · report
save_model_pred_for_one_task sel-update-mtl/utils/train_utils.py unverified MIT (permissive) · c5851b0ba58c9bd3 · report
tb_update_perf sel-update-mtl/utils/train_utils.py unverified MIT (permissive) · 3d53794e86af79d4 · report
test_phase sel-update-mtl/utils/train_utils.py unverified MIT (permissive) · ceea43c4d7d88aca · report
train_phase_affinity sel-update-mtl/utils/train_utils.py unverified MIT (permissive) · 4e9930eb324564f2 · report
update_affinity sel-update-mtl/utils/train_utils.py unverified MIT (permissive) · 6e881abbc3437293 · report
update_tb sel-update-mtl/utils/train_utils.py unverified MIT (permissive) · 07aee3dd8e23ca9c · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for SELECTIVE TASK GROUP UPDATES (graph method: SELECTIVE TASK GROUP UPDATES), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. update_proximal_inter_task_affinity entry · level 2 · ran · b9bec7e7112865a92a634e715622d5e56fbd39db42d66f2205cafcabede20e80

harvested Assembly for SELECTIVE TASK GROUP UPDATES (graph method: SELECTIVE TASK GROUP UPDATES). 17 bricks; individually on a fixture: 7 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. train_phase_affinity entry · level 0 · unverified · 4e9930eb324564f2
  2. evaluate helper · level 0 · unverified · cc95be4bcb3a1abd
  3. tb_update_perf helper · level 0 · unverified · 3d53794e86af79d4
  4. test_phase helper · level 0 · unverified · ceea43c4d7d88aca
  5. to_cuda helper · level 1 · ran; the contract check could not run (RAISES) · 48fca14a672a5108
  6. update_affinity helper · level 0 · unverified · 6e881abbc3437293
  7. update_tb helper · level 0 · unverified · 07aee3dd8e23ca9c
  8. MetricLogger helper · level 1 · ran · f5627726b4ae2bcc
  9. get_loss helper · level 1 · ran; the contract check could not run (RAISES) · 32835f4d0f551b1b
  10. get_metric helper · level 1 · ran · violated contract · 4799ae2084413fda
  11. PerformanceMeter helper · level 0 · unverified · 05242b3a981049cf
  12. get_output helper · level 1 · ran; the contract check could not run (RAISES) · a64ab65acb301c2d
  13. mkdir_if_missing helper · level 0 · unverified · 3cc281449dc70540
  14. save_model_pred_for_one_task helper · level 0 · unverified · c5851b0ba58c9bd3
  15. SmoothedValue helper · level 1 · ran · 79d5ce6f2d2f4574
  16. get_single_task_meter helper · level 0 · unverified · 6a216e80da829b4d
  17. is_dist_avail_and_initialized helper · level 1 · ran · 5f205488cb7b9004

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="2502.11986") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Multi-Task Learning

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