Papers › Meta-Consolidation for Continual Learning

Meta-Consolidation for Continual Learning

1 Oct 2020NeurIPS 2020 12arXiv:2010.00352archive 2025-07-28

K J Joseph, Vineeth N. Balasubramanian

The ability to continuously learn and adapt itself to new tasks, without losing grasp of already acquired knowledge is a hallmark of biological learning systems, which current deep learning systems fall short of. In this work, we present a novel methodology for continual learning called MERLIN: Meta-Consolidation for Continual Learning. We assume that weights of a neural network ψ, for solving task t, come from a meta-distribution p(ψ|t). This meta-distribution is learned and consolidated incrementally. We operate in the challenging online continual learning setting, where a data point is seen by the model only once. Our experiments with continual learning benchmarks of MNIST, CIFAR-10, CIFAR-100 and Mini-ImageNet datasets show consistent improvement over five baselines, including a recent state-of-the-art, corroborating the promise of MERLIN.

PaperPDFConference PDFCodeCode 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 20 code samples harvested from 1 repository linked to this paper: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 4 ran (2 with no instrument failure; 2 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.

JosephKJ/merlin officialmentioned in papermentioned on GitHubpytorchSyntology: 20 samples, 4 ran (2 instrument-failed) · 16 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

20 samples harvested: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 16 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.

2ran · our draft was wrong
2ran
16unverified

Licence: 20 of the 20 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 JosephKJ/merlin. “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.

JosephKJ/merlin official repository 20 samples, 4 ran (2 instrument-failed) · 16 unverified
Metrics lib/consolidate.py ran no licence file found · pointer only · 4f1c61003fbdaab9 · report fixture: returned Metrics · level recorded 2026-09-22
construct_state_dict_from_weights lib/consolidate.py ran · our draft was wrong no licence file found · pointer only · 13ec5834ed19bd95 · report fixture: returned dict · level recorded 2026-09-22
gen_bar_updater lib/consolidate.py ran no licence file found · pointer only · 69c291c8cf8a5818 · report fixture: returned function · level recorded 2026-09-22
one_hot in 150 papers
census: 18 implementations from 25 papers, 10 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 1 of 6, arg 1: rank 1, kind int, dtype int64
lib/consolidate.py ran · our draft was wrong no licence file found · pointer only · 8431f92b5e9cab82 · report fixture: returned Tensor · level recorded 2026-09-22
CHUNKED_VAE lib/consolidate.py unverified no licence file found · pointer only · d4dbd015944bacde · report
MNIST in 12 papers lib/consolidate.py unverified no licence file found · pointer only · b82ee827d83c2eff · report
compute_accuracy in 81 papers lib/consolidate.py unverified no licence file found · pointer only · 6d1affa42db4b765 · report
compute_offset lib/consolidate.py unverified no licence file found · pointer only · 79feca99ba9abfe0 · report
decode_chunked_model lib/consolidate.py unverified no licence file found · pointer only · b0e208a3661a619b · report
ensemble_and_evaluate lib/consolidate.py unverified no licence file found · pointer only · 5813ce0c4f476a48 · report
ensemble_and_evaluate_cumulative_prior lib/consolidate.py unverified no licence file found · pointer only · da193d4ba7529139 · report
ensembled_prediction_for_a_task lib/consolidate.py unverified no licence file found · pointer only · f9eaee6cea9ea9a5 · report
evaluate_classification_model lib/consolidate.py unverified no licence file found · pointer only · d2dd1ab69b49be0e · report
get_classification_loss lib/consolidate.py unverified no licence file found · pointer only · 52adafc4af204ff6 · report
get_weights_from_chunked_vae lib/consolidate.py unverified no licence file found · pointer only · ee8b54e47e727fb2 · report
get_weights_from_chunked_vae_cumulative_prior lib/consolidate.py unverified no licence file found · pointer only · fd90c498ce78b6f1 · report
log in 61 papers
census: 10 implementations from 16 papers, 7 distinct outputs on one shared input
lib/consolidate.py unverified no licence file found · pointer only · 92a8f98b9d4d4a77 · report
recall in 38 papers lib/consolidate.py unverified no licence file found · pointer only · 8116d3e7e4ec6a28 · report
train_block_chunk lib/consolidate.py unverified no licence file found · pointer only · 4fdf6fab77d964a3 · report
train_vae lib/consolidate.py unverified no licence file found · pointer only · 6d62cdee8d38351f · 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 MERLIN: Meta-Consolidation for Continual Learning (graph method: MERLIN: Meta-Consolidation for Continual Learning). 20 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 16 unverified. The assembly has not been run end-to-end.

  1. train_vae entry · level 0 · unverified · 6d62cdee8d38351f
  2. CHUNKED_VAE model · level 0 · unverified · d4dbd015944bacde
  3. decode_chunked_model model · level 0 · unverified · b0e208a3661a619b
  4. evaluate_classification_model helper · level 0 · unverified · d2dd1ab69b49be0e
  5. log helper · level 0 · unverified · 92a8f98b9d4d4a77
  6. one_hot helper · level 1 · ran · our draft was wrong · 8431f92b5e9cab82
  7. recall helper · level 0 · unverified · 8116d3e7e4ec6a28
  8. train_block_chunk helper · level 0 · unverified · 4fdf6fab77d964a3
  9. construct_state_dict_from_weights helper · level 1 · ran · our draft was wrong · 13ec5834ed19bd95
  10. ensemble_and_evaluate helper · level 0 · unverified · 5813ce0c4f476a48
  11. ensemble_and_evaluate_cumulative_prior helper · level 0 · unverified · da193d4ba7529139
  12. get_weights_from_chunked_vae helper · level 0 · unverified · ee8b54e47e727fb2
  13. get_weights_from_chunked_vae_cumulative_prior helper · level 0 · unverified · fd90c498ce78b6f1
  14. get_classification_loss loss · level 0 · unverified · 52adafc4af204ff6
  15. ensembled_prediction_for_a_task helper · level 0 · unverified · f9eaee6cea9ea9a5
  16. MNIST helper · level 0 · unverified · b82ee827d83c2eff
  17. compute_offset helper · level 0 · unverified · 79feca99ba9abfe0
  18. Metrics helper · level 1 · ran · 4f1c61003fbdaab9
  19. compute_accuracy helper · level 0 · unverified · 6d1affa42db4b765
  20. gen_bar_updater helper · level 1 · ran · 69c291c8cf8a5818

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="2010.00352") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continual 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