Papers › Pseudo-Rehearsal for Continual Learning with Normalizing Flows

Pseudo-Rehearsal for Continual Learning with Normalizing Flows

5 Jul 2020ICML Workshop LifelongML 2020 7arXiv:2007.02443archive 2025-07-28

Jary Pomponi, Simone Scardapane, Aurelio Uncini

Catastrophic forgetting (CF) happens whenever a neural network overwrites past knowledge while being trained on new tasks. Common techniques to handle CF include regularization of the weights (using, e.g., their importance on past tasks), and rehearsal strategies, where the network is constantly re-trained on past data. Generative models have also been applied for the latter, in order to have endless sources of data. In this paper, we propose a novel method that combines the strengths of regularization and generative-based rehearsal approaches. Our generative model consists of a normalizing flow (NF), a probabilistic and invertible neural network, trained on the internal embeddings of the network. By keeping a single NF conditioned on the task, we show that our memory overhead remains constant. In addition, exploiting the invertibility of the NF, we propose a simple approach to regularize the network's embeddings with respect to past tasks. We show that our method performs favorably with respect to state-of-the-art approaches in the literature, with bounded computational power and memory overheads.

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 21 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 11 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: 21 samples from 1 repository, 10 ran (8 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 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.

ispamm/PRER officialmentioned in paperpytorchSyntology: 21 samples, 10 ran (2 instrument-failed) · 11 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

21 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 11 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
8ran
11unverified

Licence: 21 of the 21 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 ispamm/PRER. “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.

ispamm/PRER official repository 21 samples, 10 ran (2 instrument-failed) · 11 unverified
BatchNorm in 19 papers continual_ai/cl_strategies/multi_task/prer/PRER.py ran fingerprinted no licence file found · pointer only · 3fa807854aaa4305 · report fixture: signature x:Tensor/2/float · returned tuple · level recorded 2026-09-24
Conditioner continual_ai/cl_strategies/multi_task/prer/PRER.py ran · metamorphic tier: invariant no licence file found · pointer only · d43422026fb01a01 · report fixture: signature y:Tensor/1/int · returned Tensor · level recorded 2026-09-22
CouplingLayer in 11 papers continual_ai/cl_strategies/multi_task/prer/PRER.py ran · metamorphic tier: deterministic no licence file found · pointer only · 83607333c7fc8258 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned tuple · level recorded 2026-09-22
Encoder in 278 papers continual_ai/cl_strategies/multi_task/prer/PRER.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 200fa3e04941e661 · report fixture: signature x:Tensor/4/float, y:NoneType/0/? · returned Tensor · level recorded 2026-09-22
NoneConditioner continual_ai/cl_strategies/multi_task/prer/PRER.py ran · metamorphic tier: deterministic no licence file found · pointer only · 52cca2a1c5d32c72 · report fixture: signature args:tuple/1/empty, kwargs:dict/0/? · returned NoneType · level recorded 2026-09-22
Prior continual_ai/cl_strategies/multi_task/prer/PRER.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · c28cb8903e6fa746 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Reshape in 7 papers continual_ai/cl_strategies/multi_task/prer/PRER.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 764a0379bdcee1c3 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Split continual_ai/cl_strategies/multi_task/prer/PRER.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · f35198d0074078c5 · report fixture: signature x:Tensor/2/float, y:NoneType/0/? · returned tuple · level recorded 2026-09-22
gaussian_nll in 8 papers continual_ai/cl_strategies/multi_task/prer/PRER.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 4eaf1511053dc8a7 · report fixture: signature mu:Tensor/2/float, log_sigma:Tensor/2/float, x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
reconstruction_loss in 14 papers continual_ai/cl_strategies/multi_task/prer/PRER.py ran · our draft was wrong fingerprinted no licence file found · pointer only · ad91a710aa97e44c · report fixture: signature x:Tensor/4/float, x_hat:Tensor/4/float, softclip:int/0/int, reduction:str/0/str · returned Tensor · level recorded 2026-09-22
Container continual_ai/cl_strategies/multi_task/prer/PRER.py unverified no licence file found · pointer only · 9db2c3455ae543fd · report
Decoder in 210 papers continual_ai/cl_strategies/multi_task/prer/PRER.py unverified no licence file found · pointer only · a23dd769c98cf3a9 · report
ExperimentConfig continual_ai/cl_strategies/multi_task/prer/PRER.py unverified no licence file found · pointer only · ce218d15010f7d86 · report
NaiveMethod continual_ai/cl_strategies/multi_task/prer/PRER.py unverified no licence file found · pointer only · 18db7c3472875ddd · report
PRERproj continual_ai/cl_strategies/multi_task/prer/PRER.py unverified no licence file found · pointer only · 8dcb0d35b0a23a29 · report
Permutation in 5 papers continual_ai/cl_strategies/multi_task/prer/PRER.py unverified no licence file found · pointer only · e7d6b7ab3a5ec11f · report
RNVP continual_ai/cl_strategies/multi_task/prer/PRER.py unverified no licence file found · pointer only · 7135c7d62a514fbd · report
RNVPBlock continual_ai/cl_strategies/multi_task/prer/PRER.py unverified no licence file found · pointer only · 7959332f2d4a6086 · report
RNVPLevel continual_ai/cl_strategies/multi_task/prer/PRER.py unverified no licence file found · pointer only · c84d2d298f0a6278 · report
SequentialFlow continual_ai/cl_strategies/multi_task/prer/PRER.py unverified no licence file found · pointer only · c6fe6fda8d262a8f · report
SingleIncrementalTaskSolver continual_ai/cl_strategies/multi_task/prer/PRER.py unverified no licence file found · pointer only · 68fa55c2336ed20e · 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 Pseudo-Rehearsal (graph method: Pseudo-Rehearsal). 21 bricks; individually on a fixture: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. PRERproj entry · level 0 · unverified · 8dcb0d35b0a23a29
  2. Conditioner model · level 1 · ran · d43422026fb01a01
  3. Container helper · level 0 · unverified · 9db2c3455ae543fd
  4. Decoder helper · level 0 · unverified · a23dd769c98cf3a9
  5. Encoder helper · level 1 · ran · 200fa3e04941e661
  6. ExperimentConfig helper · level 0 · unverified · ce218d15010f7d86
  7. NaiveMethod helper · level 0 · unverified · 18db7c3472875ddd
  8. NoneConditioner helper · level 1 · ran · 52cca2a1c5d32c72
  9. Prior helper · level 1 · ran · c28cb8903e6fa746
  10. RNVP model · level 0 · unverified · 7135c7d62a514fbd
  11. SingleIncrementalTaskSolver helper · level 0 · unverified · 68fa55c2336ed20e
  12. reconstruction_loss loss · level 1 · ran · our draft was wrong · ad91a710aa97e44c
  13. Reshape helper · level 1 · ran · 764a0379bdcee1c3
  14. RNVPLevel helper · level 0 · unverified · c84d2d298f0a6278
  15. gaussian_nll loss · level 1 · ran · our draft was wrong · 4eaf1511053dc8a7
  16. RNVPBlock helper · level 0 · unverified · 7959332f2d4a6086
  17. SequentialFlow helper · level 0 · unverified · c6fe6fda8d262a8f
  18. Split helper · level 1 · ran · f35198d0074078c5
  19. BatchNorm model · level 1 · ran · 3fa807854aaa4305
  20. CouplingLayer model · level 1 · ran · 83607333c7fc8258
  21. Permutation helper · level 0 · unverified · e7d6b7ab3a5ec11f

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="2007.02443") 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