Papers › Divide and not forget: Ensemble of selectively trained experts in Continual Learning

Divide and not forget: Ensemble of selectively trained experts in Continual Learning

18 Jan 2024arXiv:2401.10191archive 2025-07-28

Grzegorz Rypeść, Sebastian Cygert, Valeriya Khan, Tomasz Trzciński, Bartosz Zieliński, Bartłomiej Twardowski

Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together to solve the task. However, the experts are usually trained all at once using whole task data, which makes them all prone to forgetting and increasing computational burden. To address this limitation, we introduce a novel approach named SEED. SEED selects only one, the most optimal expert for a considered task, and uses data from this task to fine-tune only this expert. For this purpose, each expert represents each class with a Gaussian distribution, and the optimal expert is selected based on the similarity of those distributions. Consequently, SEED increases diversity and heterogeneity within the experts while maintaining the high stability of this ensemble method. The extensive experiments demonstrate that SEED achieves state-of-the-art performance in exemplar-free settings across various scenarios, showing the potential of expert diversification through data in continual learning.

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.

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

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 9 ran (5 with no instrument failure; 4 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 9 samples that ran has no recorded date.

grypesc/seed officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 9 ran (4 instrument-failed) · 1 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

10 samples harvested: 9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 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.

3ran · our draft was wrong
1ran; the contract check could not run
5ran
1unverified

Licence: 0 of the 10 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 grypesc/seed. “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.

grypesc/seed official repository 10 samples, 9 ran (4 instrument-failed) · 1 unverified
ClassDirectoryDataset src/approach/seed.py ran MIT (permissive) · 911cc14e7fa1b63a · report fixture: returned ClassDirectoryDataset · level recorded 2026-09-22
ClassMemoryDataset src/approach/seed.py ran MIT (permissive) · e49ad10d768d006a · report fixture: returned ClassMemoryDataset · level recorded 2026-09-22
ExemplarsDataset src/approach/seed.py ran MIT (permissive) · 7dbb544669ebb01d · report fixture: signature model:callable/0/?, trn_loader:DataLoader/0/?, selection_transform:callable/0/? · returned NoneType · level recorded 2026-09-24
GaussianMixture src/approach/seed.py ran MIT (permissive) · ee35cf16bfbb70b6 · report fixture: returned GaussianMixture · level recorded 2026-09-22
Inc_Learning_Appr in 5 papers src/approach/seed.py ran MIT (permissive) · 6af6e3f22725346c · report fixture: returned Inc_Learning_Appr · level recorded 2026-09-22
calculate_matmul src/approach/seed.py ran; the contract check could not run (RAISES) MIT (permissive) · 4451964134c9d216 · report fixture: signature mat_a:Tensor/4/float, mat_b:Tensor/4/float · returned Tensor · level recorded 2026-09-22
calculate_matmul_n_times src/approach/seed.py ran · our draft was wrong MIT (permissive) · fa6374ff7f7939f4 · report fixture: signature n_components:int/0/int, mat_a:Tensor/4/float, mat_b:Tensor/4/float · returned Tensor · level recorded 2026-09-22
softmax_temperature src/approach/seed.py ran · our draft was wrong fingerprinted MIT (permissive) · c1cbed26c18dd1f2 · report fixture: signature x:Tensor/2/float, dim:int/0/int, tau:float/0/float · returned Tensor · level recorded, date not recorded
softmax_temperature src/approach/seed.py ran · our draft was wrong fingerprinted MIT (permissive) · 56730f951de5fd44 · report fixture: signature x:Tensor/2/float, dim:int/0/int, tau:float/0/float · returned Tensor · level recorded 2026-09-22
Appr in 8 papers src/approach/seed.py unverified MIT (permissive) · 9a8759c93a1ea172 · 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 SEED (graph method: SEED). 11 bricks; individually on a fixture: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. Appr entry · level 0 · unverified · 9a8759c93a1ea172
  2. ClassDirectoryDataset helper · level 1 · ran · 911cc14e7fa1b63a
  3. ClassMemoryDataset helper · level 1 · ran · e49ad10d768d006a
  4. GaussianMixture helper · level 1 · ran · ee35cf16bfbb70b6
  5. Inc_Learning_Appr helper · level 1 · ran · 6af6e3f22725346c
  6. softmax_temperature helper · level 1 · ran · our draft was wrong · 56730f951de5fd44
  7. calculate_matmul helper · level 1 · ran; the contract check could not run (RAISES) · 4451964134c9d216
  8. calculate_matmul_n_times helper · level 1 · ran · our draft was wrong · fa6374ff7f7939f4
  9. ExemplarsDataset helper · level 1 · ran · 7dbb544669ebb01d
  10. ExperimentLogger helper · level 1 · ran · 1d10e03aa48307d3
  11. MemoryDataset helper · level 1 · ran · c1ecdf9c6eed882e

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="2401.10191") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Class Incremental LearningContinual LearningDiversityExemplar-FreeIncremental Learningclass-incremental learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Class Incremental Learning CIFAR100-B0(50 tasks)-no-exemplars SEED Average Incremental Accuracy 42.6 #1 of 1 Archive leaderboard report
Class Incremental Learning Cifar100-B0(10 tasks)-no-exemplars SEED Average Incremental Accuracy 61.7 #1 of 1 Archive leaderboard report
Class Incremental Learning Cifar100-B0(20 tasks)-no-exemplars SEED Average Incremental Accuracy 56.2 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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