Papers › Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning

Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning

5 Dec 2021NeurIPS 2021 12arXiv:2112.02706archive 2025-07-28

Zixuan Ke, Bing Liu, Nianzu Ma, Hu Xu, Lei Shu

Continual learning (CL) learns a sequence of tasks incrementally with the goal of achieving two main objectives: overcoming catastrophic forgetting (CF) and encouraging knowledge transfer (KT) across tasks. However, most existing techniques focus only on overcoming CF and have no mechanism to encourage KT, and thus do not do well in KT. Although several papers have tried to deal with both CF and KT, our experiments show that they suffer from serious CF when the tasks do not have much shared knowledge. Another observation is that most current CL methods do not use pre-trained models, but it has been shown that such models can significantly improve the end task performance. For example, in natural language processing, fine-tuning a BERT-like pre-trained language model is one of the most effective approaches. However, for CL, this approach suffers from serious CF. An interesting question is how to make the best use of pre-trained models for CL. This paper proposes a novel model called CTR to solve these problems. Our experimental results demonstrate the effectiveness of CTR

PaperPDFConference PDFCode

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

Code

zixuanke/pycontinual officialmentioned in paperpytorch 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Continual LearningLanguage ModelingLanguage ModellingSentiment AnalysisTransfer Learning

Datasets

Introduced by this paper, per the archive.

20Newsgroup (10 tasks)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Continual Learning 20Newsgroup (10 tasks) CTR F1 - macro 0.9523 #1 of 6 Archive leaderboard report
Continual Learning ASC (19 tasks) Multi-task Learning (MTL; Upper Bound) F1 - macro 0.8811 #1 of 15 Archive leaderboard report
Continual Learning ASC (19 tasks) CTR F1 - macro 0.8362 #2 of 15 Archive leaderboard report
Continual Learning ASC (19 tasks) Independent Learning (ONE) F1 - macro 0.7807 #8 of 15 Archive leaderboard report
Continual Learning ASC (19 tasks) Naive Continual Learning (NCL) F1 - macro 0.7664 #10 of 15 Archive leaderboard report
Continual Learning DSC (10 tasks) CTR F1 - macro 0.8875 #1 of 6 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.

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