SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.02443 · ICML · 2020

Pseudo-Rehearsal for Continual Learning with Normalizing Flows

Jary Pomponi, Simone Scardapane, Aurelio Uncini

arXiv · PDF · Open in the Atlas

Code that ran

10 of 21 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 2 failures of our instrument; 11 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/2007.02443.json · badge: /api/ran/2007.02443.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
ispamm/PRER marked official in Papers with Code
Papers with Code archive
10 ran · 11 no recorded run
FunctionStatusWhere it lives
BatchNorm Ran
ran on a synthesized input
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("3fa807854aaa4305")
How it ran

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

Conditioner Ran
ran on a synthesized input
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("d43422026fb01a01")
How it ran

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

CouplingLayer Ran
ran on a synthesized input
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("83607333c7fc8258")
How it ran

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

Encoder Ran
ran on a synthesized input
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("200fa3e04941e661")
How it ran

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

NoneConditioner Ran
ran on a synthesized input
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("52cca2a1c5d32c72")
How it ran

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

Prior Ran
ran on a synthesized input
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("c28cb8903e6fa746")
How it ran

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

Reshape Ran
ran on a synthesized input
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("764a0379bdcee1c3")
How it ran

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

Split Ran
ran on a synthesized input
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("f35198d0074078c5")
How it ran

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

gaussian_nll Ran
ran; our contract draft was wrong, not the code
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("4eaf1511053dc8a7")
How it ran

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

reconstruction_loss Ran
ran; our contract draft was wrong, not the code
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("ad91a710aa97e44c")
How it ran

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

Container Not yet run
unverified (harvested, no recorded run)
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("9db2c3455ae543fd")
How it ran

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

Decoder Not yet run
unverified (harvested, no recorded run)
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("a23dd769c98cf3a9")
How it ran

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

ExperimentConfig Not yet run
unverified (harvested, no recorded run)
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("ce218d15010f7d86")
How it ran

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

NaiveMethod Not yet run
unverified (harvested, no recorded run)
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("18db7c3472875ddd")
How it ran

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

PRERproj Not yet run
unverified (harvested, no recorded run)
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("8dcb0d35b0a23a29")
How it ran

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

Permutation Not yet run
unverified (harvested, no recorded run)
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("e7d6b7ab3a5ec11f")
How it ran

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

RNVP Not yet run
unverified (harvested, no recorded run)
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("7135c7d62a514fbd")
How it ran

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

RNVPBlock Not yet run
unverified (harvested, no recorded run)
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("7959332f2d4a6086")
How it ran

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

RNVPLevel Not yet run
unverified (harvested, no recorded run)
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("c84d2d298f0a6278")
How it ran

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

SequentialFlow Not yet run
unverified (harvested, no recorded run)
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("c6fe6fda8d262a8f")
How it ran

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

SingleIncrementalTaskSolver Not yet run
unverified (harvested, no recorded run)
ispamm/PRER/continual_ai/cl_strategies/multi_task/prer/PRER.py
pointer only (licence: NONE) · get_code("68fa55c2336ed20e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ispamm/PRER 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 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 21 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 20 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
gaussian_nll
brick of this paper's assembly: loss
1 other paper
1 dated earlier
2006.13202 (2020-06)
Simple and Effective VAE Training with Calibrated Decoders

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

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.

For agents

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

get_harvested_code_for_paper("2007.02443")
get_code_for_paper("2007.02443")
have("2007.02443")

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

curl https://syntology.ai/api/ran/2007.02443.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.02443.svg)](https://syntology.ai/paper/2007.02443)

Connect an agent — have() is free.