Papers › Efficient Lifelong Learning with A-GEM

Efficient Lifelong Learning with A-GEM

2 Dec 2018ICLR 2019 5arXiv:1812.00420archive 2025-07-28

Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, Mohamed Elhoseiny

In lifelong learning, the learner is presented with a sequence of tasks, incrementally building a data-driven prior which may be leveraged to speed up learning of a new task. In this work, we investigate the efficiency of current lifelong approaches, in terms of sample complexity, computational and memory cost. Towards this end, we first introduce a new and a more realistic evaluation protocol, whereby learners observe each example only once and hyper-parameter selection is done on a small and disjoint set of tasks, which is not used for the actual learning experience and evaluation. Second, we introduce a new metric measuring how quickly a learner acquires a new skill. Third, we propose an improved version of GEM (Lopez-Paz & Ranzato, 2017), dubbed Averaged GEM (A-GEM), which enjoys the same or even better performance as GEM, while being almost as computationally and memory efficient as EWC (Kirkpatrick et al., 2016) and other regularization-based methods. Finally, we show that all algorithms including A-GEM can learn even more quickly if they are provided with task descriptors specifying the classification tasks under consideration. Our experiments on several standard lifelong learning benchmarks demonstrate that A-GEM has the best trade-off between accuracy and efficiency.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1812.00420")

Code

Syntology Ran 1 of 12 code samples harvested from 1 repository linked to this paper; 11 have no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: official repository: 12 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/agem officialmentioned in papermentioned on GitHubtf 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

12 samples harvested; 1 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
11unverified

Licence: 0 of the 12 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 facebookresearch/agem. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

create_fc_layer facebookresearch/agem/model/model.py official repository ran · fixture could not drive it MIT (permissive) · f5ffbe87b7ec7cb6 · report
Model facebookresearch/agem/model/model.py official repository unverified MIT (permissive) · fc44c3b7614307dc · report
_bn facebookresearch/agem/model/model.py official repository unverified MIT (permissive) · 60a81bb1d1fb0b67 · report
_conv facebookresearch/agem/model/model.py official repository unverified MIT (permissive) · 0562f5e312d29cbd · report
_fc facebookresearch/agem/model/model.py official repository unverified MIT (permissive) · 3de3229cf0087e10 · report
_residual_block facebookresearch/agem/model/model.py official repository unverified MIT (permissive) · 6a7664c18c49e6ba · report
_residual_block_first facebookresearch/agem/model/model.py official repository unverified MIT (permissive) · 5cfb34725fa7d7cc · report
bias_variable facebookresearch/agem/model/model.py official repository unverified MIT (permissive) · a96da1b71ad1a9ef · report
create_conv_layer facebookresearch/agem/model/model.py official repository unverified MIT (permissive) · 4531aa012b415174 · report
vgg_conv_layer facebookresearch/agem/model/model.py official repository unverified MIT (permissive) · 3dd896a5062484eb · report
vgg_fc_layer facebookresearch/agem/model/model.py official repository unverified MIT (permissive) · b1b9b69ee1f47548 · report
weight_variable facebookresearch/agem/model/model.py official repository unverified MIT (permissive) · 70fae4aed55bdadc · report

Tasks

Class Incremental LearningContinual LearningLifelong learningclass-incremental learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Class Incremental Learning cifar100 A-GEM 10-stage average accuracy 45.76 #7 of 7 Archive leaderboard report
Continual Learning ASC (19 tasks) A-GEM F1 - macro 0.7844 #6 of 15 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.

Methods

SPEED

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