Papers › Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks

Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks

18 Dec 2021NeurIPS 2020 12arXiv:2112.10017archive 2025-07-28

Zixuan Ke, Bing Liu, Xingchang Huang

Existing research on continual learning of a sequence of tasks focused on dealing with catastrophic forgetting, where the tasks are assumed to be dissimilar and have little shared knowledge. Some work has also been done to transfer previously learned knowledge to the new task when the tasks are similar and have shared knowledge. To the best of our knowledge, no technique has been proposed to learn a sequence of mixed similar and dissimilar tasks that can deal with forgetting and also transfer knowledge forward and backward. This paper proposes such a technique to learn both types of tasks in the same network. For dissimilar tasks, the algorithm focuses on dealing with forgetting, and for similar tasks, the algorithm focuses on selectively transferring the knowledge learned from some similar previous tasks to improve the new task learning. Additionally, the algorithm automatically detects whether a new task is similar to any previous tasks. Empirical evaluation using sequences of mixed tasks demonstrates the effectiveness of the proposed model.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

ZixuanKe/CAT officialmentioned in paperpytorch report
zixuanke/pycontinual officialpytorch 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 Learning

Datasets

Introduced by this paper, per the archive.

F-CelebA (10 tasks)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Continual Learning 20Newsgroup (10 tasks) CAT F1 - macro 0.9516 #3 of 6 Archive leaderboard report
Continual Learning ASC (19 tasks) CAT F1 - macro 0.6864 #14 of 15 Archive leaderboard report
Continual Learning DSC (10 tasks) CAT F1 - macro 0.8651 #2 of 6 Archive leaderboard report
Continual Learning F-CelebA (10 tasks) CAT (CNN backbone) Acc 0.7564 #1 of 7 Archive leaderboard report
Continual Learning F-CelebA (10 tasks) CAT (MLP backbone) Acc 0.6909 #2 of 7 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