AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning

Bokun Wang, Zhuoning Yuan, Yiming Ying, Tianbao Yang

JMLR 2023 · Federated learning and privacy › Communication-efficient FL · approach: Local drift correction · 15 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
add MOML-v1 memory-based update instead of MAML (BSGD)MAML · Sinewave regression (K=1)avg test error: 0.889 -> 0.291Improved
use MOML-v1 instead of MAML (BSGD)MAML · Sinewave regression (K=3)avg test error: 0.321 -> 0.196Improved
use MOML-v2 instead of MOML-v1 (update all n personalized models)MOML · Sinewave regression (K=1)avg test error: 0.291 -> 0.448Hurt
use MOML-v2 instead of MOML-v1MOML · Sinewave regression (K=1)avg time per iteration (ms): 2.180 -> 7.863Hurt
use LocalMOML instead of MOML-v1MOML · Sinewave regression (K=3)avg test error: 0.196 -> 0.170Improved
use MOML-v1 instead of MAML (BSGD)MAML · Omniglot 20-way one-shottest accuracy (%): 44.31 -> 46.35Improved
use MOML-v2 instead of MAML (BSGD)MAML · CIFAR-100 5-way one-shottest accuracy (%): 40.18 -> 40.82Improved
use LocalMOML instead of Per-FedAvgPer-FedAvg · CIFAR-100 federated 5-shot (H=10, B'=5 tasks per GPU)test accuracy (%): 53.37 -> 56.45Improved
use LocalMOML instead of pFedMepFedMe · CIFAR-100 federated 5-shot (H=4, B'=1 tasks per GPU)test accuracy (%): 49.64 -> 54.00Improved
use LocalMOML instead of Per-FedAvgPer-FedAvg · CIFAR-10 federated 5-shot (H=4, B'=1 tasks per GPU)test accuracy (%): 63.81 -> 66.16Improved
use LocalMOML instead of Per-FedAvgPer-FedAvg · MNIST federated 5-shot (H=4, B'=1 tasks per GPU)test accuracy (%): 91.63 -> 91.62No clear effect
use ProtoNet instead of MAML (BSGD)MAML · CIFAR-100 5-way one-shottest accuracy (%): 40.18 -> 31.11Hurt

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