AI Paper Atlas

Research map / Continual learning / Online and replay-based

Less Is More in Federated Continual Learning: RieSelect for Conflict-Aware Layer Selection in LLMs

Wenqi Qiu, Yipeng Zhou, Lin Zhu, Laizhong Cui

ICML 2026 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks

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
add Step 2 Riemannian safe-step adjustment (ablation)RieSelect · SuperNI Order 2 (LLaMA2-7B)AA: 32.98 -> 44.46Improved
add Step 2 Riemannian safe-step adjustment (ablation)RieSelect · SuperNI Order 2 (LLaMA2-7B)BWT: -15.44 -> 5.08Improved
add Step 3 knapsack layer selection (ablation)RieSelect · SuperNI Order 2 (LLaMA2-7B)AA: 34.46 -> 44.46Improved
add Step 3 knapsack layer selection (ablation)RieSelect · SuperNI Order 2 (LLaMA2-7B)BWT: 2.32 -> 5.08Improved
add Step 2 Riemannian safe-step adjustment (ablation)RieSelect · LongSeq Order 3 (LLaMA2-7B)AA: 35.23 -> 73.39Improved
add Step 2 Riemannian safe-step adjustment (ablation)RieSelect · LongSeq Order 3 (LLaMA2-7B)BWT: -38.18 -> 6.13Improved
add Step 3 knapsack layer selection (ablation)RieSelect · LongSeq Order 3 (LLaMA2-7B)AA: 39.96 -> 73.39Improved
add Step 3 knapsack layer selection (ablation)RieSelect · LongSeq Order 3 (LLaMA2-7B)BWT: 3.79 -> 6.13Improved
set safe-basin radius R_eps to 10 instead of smaller or larger values (ablation)RieSelect · SuperNI Order 2 (LLaMA2-7B)AA and BWT: R_eps = 10 best AA and only positive BWTMixed
upload all layers instead of a budget-matched Top-K subset (increase transmitted-layer ratio beyond moderate level)LoRA-based FCL · Transmitted-layer ratio sweepAANo clear effect
revert the top-conflict uploaded layers versus random layers (ablation)Full-uplink LoRA FCL · Reversion study (Fig. 1c-d)BWT and new-task accuracyImproved
apply budget-matched Top-K layer upload to baselinesbaselines (LoRA, EWC, A-GEM, etc.) · LLaMA2-7B Order 3 matched budgetFinal AAHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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