Papers › Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning

Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning

5 Apr 2019CVPR 2019 6arXiv:1904.03137archive 2025-07-28

Oleksiy Ostapenko, Mihai Puscas, Tassilo Klein, Patrick Jähnichen, Moin Nabi

Models trained in the context of continual learning (CL) should be able to learn from a stream of data over an undefined period of time. The main challenges herein are: 1) maintaining old knowledge while simultaneously benefiting from it when learning new tasks, and 2) guaranteeing model scalability with a growing amount of data to learn from. In order to tackle these challenges, we introduce Dynamic Generative Memory (DGM) - a synaptic plasticity driven framework for continual learning. DGM relies on conditional generative adversarial networks with learnable connection plasticity realized with neural masking. Specifically, we evaluate two variants of neural masking: applied to (i) layer activations and (ii) to connection weights directly. Furthermore, we propose a dynamic network expansion mechanism that ensures sufficient model capacity to accommodate for continually incoming tasks. The amount of added capacity is determined dynamically from the learned binary mask. We evaluate DGM in the continual class-incremental setup on visual classification tasks.

PaperPDFConference PDFCode

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

Code

SAP-archive/machine-learning-dgm mentioned on GitHubpytorchNOASSERTION report
SAP/machine-learning-dgm mentioned on GitHubpytorchNOASSERTION 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

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Continual Learning ImageNet-50 (5 tasks) DGMw Accuracy 17.82 #4 of 5 Archive leaderboard report
Continual Learning ImageNet-50 (5 tasks) DGMa Accuracy 15.16 #5 of 5 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