AI Paper Atlas

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

Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction

Hanhan Zhou, Tian Lan, Guru Prasadh Venkataramani, Wenbo Ding

NeurIPS 2023 · Federated learning and privacy › Communication-efficient FL · approach: Efficient local training in FL · 11 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
Increase minimum coverage index through optimized client-model distribution rather than greedy pruningPruning-Greedy · MNIST IID, high model reductionaccuracy: 95.01 -> 95.32Improved
Increase minimum coverage index through optimized client-model distribution rather than greedy pruningPruning-Greedy · MNIST non-IID L=2, high model reductionaccuracy: 76.64 -> 81.66Improved
Increase minimum coverage index through optimized client-model distribution rather than greedy pruningPruning-Greedy · CIFAR-10 IID, high model reductionaccuracy: 67.35 -> 67.74Improved
Increase minimum coverage index through optimized client-model distribution rather than greedy pruningPruning-Greedy · CIFAR-10 non-IID L=2, high model reductionaccuracy: 22.55 -> 27.97Improved
Increase minimum coverage index through optimized client-model distribution rather than greedy pruningPruning-Greedy · CIFAR100 IID, high model reductionaccuracy: 39.29 -> 40.78Improved
Increase minimum coverage index through optimized client-model distribution rather than greedy pruningPruning-Greedy · CIFAR100 non-IID L=20, high model reductionaccuracy: 25.97 -> 26.63Improved
Distribute extracted subnet regions across clients instead of keeping only leading subnet parametersStatic Subnet Subtraction · MNIST IID, high model reductionaccuracy: 95.88 -> 94.41Hurt
Distribute extracted subnet regions across clients instead of keeping only leading subnet parametersStatic Subnet Subtraction · MNIST non-IID L=2, high model reductionaccuracy: 71.64 -> 85.82Improved
Distribute extracted subnet regions across clients instead of keeping only leading subnet parametersStatic Subnet Subtraction · CIFAR-10 IID, high model reductionaccuracy: 68.78 -> 69.15Improved
Distribute extracted subnet regions across clients instead of keeping only leading subnet parametersStatic Subnet Subtraction · CIFAR-10 non-IID L=2, high model reductionaccuracy: 30.61 -> 33.46Improved
Distribute extracted subnet regions across clients instead of keeping only leading subnet parametersStatic Subnet Subtraction · CIFAR100 IID, high model reductionaccuracy: 41.18 -> 37.42Hurt
Distribute extracted subnet regions across clients instead of keeping only leading subnet parametersStatic Subnet Subtraction · CIFAR100 non-IID L=20, high model reductionaccuracy: 26.23 -> 22.40Hurt

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