AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Learning to Collaborate: An Orchestrated-Decentralized Framework for Peer-to-Peer LLM Federation

Inderjeet Singh, Eleonore Vissol-Gaudin, Andikan Otung, Motoyoshi Sekiya

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 3 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
replace random P2P pairing with LinUCB matchmaking (CPM) (ablation)P2P distillation · HumanEval+MBPP, 6 clientsPass@1 (%): 8.89 -> 13.33Improved
replace data-diversity heuristic pairing with learned CPM (ablation)P2P distillation · HumanEval+MBPP, 6 clientsPass@1 (%): 6.67 -> 13.33Improved
pair clients by maximizing JS divergence instead of random (ablation)P2P distillation · HumanEval+MBPP, 6 clientsPass@1 (%): 8.89 -> 6.67Hurt
add P2P collaboration over isolated trainingLLM agents · HumanEval+MBPP, 6 clientsPass@1 (%): 2.22 -> 8.89Improved
use centralized averaged-logit KD instead of P2PLLM agents · HumanEval+MBPP, 6 clientsPass@1 (%): 18.33 -> 2.00Hurt
use FedID-CentralKD server teacherLLM agents · HumanEval+MBPP, 6 clientsPass@1 (%): 2.22 -> 1.11Hurt
use CPM-guided pairing instead of random (ablation)P2P distillation · Transfer set peak studentPass@1 (%): 33.33 -> 86.70Improved
use LinUCB CPM vs random pairing, high heterogeneity (ablation)P2P distillation · Synthetic 32 clientsrelative gain (%): 48.5Improved
use LinUCB CPM vs random pairing, low heterogeneity (ablation)P2P distillation · Synthetic low heterogeneityrelative gain (%): 3.1No clear effect
heuristic pairing improves CodeBLEU over CPM (ablation)Heuristic-P2P · HumanEval+MBPP, 6 clientsCodeBLEU: 0.344 -> 0.392Mixed

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