AI Paper Atlas

Research map / Continual learning / Online and replay-based

Beyond Sharpness: A Flatness Decomposition Framework for Efficient Continual Learning

Yanan Chen, Tieliang Gong, Yunjiao Zhang, Wen Wen

AAAI 2026 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
plug in FLAD optimizerReplay · CIFAR-100 (10 tasks)Acc: 29.07 -> 31.74Improved
plug in FLAD optimizerPODNet · CIFAR-100 (10 tasks)Acc: 31.87 -> 34.85Improved
plug in FLAD optimizerWA · CIFAR-100 (10 tasks)Acc: 47.29 -> 48.35Improved
plug in FLAD optimizeriCaRL · CIFAR-100 (10 tasks)Acc: 30.05 -> 30.36No clear effect
plug in FLAD optimizerFOSTER · CIFAR-100 (10 tasks)Acc: 39.71 -> 39.13Hurt
plug in FLAD optimizerMEMO · CIFAR-100 (10 tasks)Acc: 53.27 -> 53.92Mixed
plug in FLAD optimizerReplay · Tiny-ImageNet (8 tasks)Acc: 19.09 -> 22.91Improved
plug in FLAD optimizerFOSTER · CIFAR-10 (5 tasks)AAA: 65.15 -> 75.08Improved
use stochastic-noise perturbation instead of full-gradient perturbation (ablation)GAM · CIFAR-10/100 ResNetaverage accuracyImproved
set gamma = 0 (drop first-order term) (ablation)FLAD · CIFAR-100accuracyImproved
use decomposed (noise) gradient variant instead of original (ablation)FLAD-0th / FLAD-1st · 6 CL methodsaccuracyImproved
apply FLAD in only 10-20% of epochs (ablation)FLAD · CIFAR-100 Replayaccuracy / training timeImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy