SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.06976 · ICLR · 2022

Representational Continuity for Unsupervised Continual Learning

Jaehong Yoon, Divyam Madaan, Yuanchun Li, Yunxin Liu, Sung Ju Hwang

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure of our instrument; 2 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/2110.06976.json · badge: /api/ran/2110.06976.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
divyam3897/ucl canonical (classifier label)
classifier basis: classifier_2025
4 ran · 2 no recorded run
FunctionStatusWhere it lives
Buffer Ran
ran on a synthesized input · constructed an object; no result was computed
divyam3897/ucl/models/mixup.py
pointer only (licence: NOASSERTION) · get_code("60c8f08559dd5eba")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, divyam3897/ucl (NOASSERTION). 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.

LARS Ran
ran on a synthesized input · constructed an object; no result was computed
divyam3897/ucl/models/mixup.py
pointer only (licence: NOASSERTION) · get_code("cbc529c692526afb")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, divyam3897/ucl (NOASSERTION). 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.

LR_Scheduler Ran
ran on a synthesized input · constructed an object; no result was computed
divyam3897/ucl/models/mixup.py
pointer only (licence: NOASSERTION) · get_code("812d838b69cc5520")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, divyam3897/ucl (NOASSERTION). 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.

get_optimizer Ran
ran; our contract draft was wrong, not the code
divyam3897/ucl/models/mixup.py
pointer only (licence: NOASSERTION) · get_code("c3afd56f1b041572")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, divyam3897/ucl (NOASSERTION). 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.

ContinualModel Not yet run
unverified (harvested, no recorded run)
divyam3897/ucl/models/mixup.py
pointer only (licence: NOASSERTION) · get_code("903bc2472f853661")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, divyam3897/ucl (NOASSERTION). 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.

Mixup Not yet run
unverified (harvested, no recorded run)
divyam3897/ucl/models/mixup.py
pointer only (licence: NOASSERTION) · get_code("8c6f91057e597c0a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, divyam3897/ucl (NOASSERTION). 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable to real-world applications where the data distribution is often biased and unannotated. In this work, we focus on unsupervised continual learning (UCL), where we learn the feature representations on an unlabelled sequence of tasks and show that reliance on annotated data is not necessary for continual learning. We conduct a systematic study analyzing the learned feature representations and show that unsupervised visual representations are surprisingly more robust to catastrophic forgetting, consistently achieve better performance, and generalize better to out-ofdistribution tasks than SCL. Furthermore, we find that UCL achieves a smoother loss landscape through qualitative analysis of the learned representations and learns meaningful feature representations. Additionally, we propose Lifelong Unsupervised Mixup (LUMP), a simple yet effective technique that interpolates between the current task and previous tasks' instances to alleviate catastrophic forgetting for unsupervised representations. We release our code online.

For agents

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

get_harvested_code_for_paper("2110.06976")
get_code_for_paper("2110.06976")
have("2110.06976")

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

curl https://syntology.ai/api/ran/2110.06976.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.06976.svg)](https://syntology.ai/paper/2110.06976)

Connect an agent — have() is free.