AI Paper Atlas

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

CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference

Wenxuan Zeng, Meng Li, Haichuan Yang, Wen-jie Lu, Runsheng Wang, Ru Huang

NeurIPS 2023 · Federated learning and privacy › Communication-efficient FL · approach: Decentralized peer-to-peer training · 2 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
rewrite Winograd EWMM as GEMM with tile aggregation (ablation)Winograd conv protocol · ResNet-18 blockcommunication (GB): 256 -> 10.45Improved
add DNN-aware adaptive sender selection (ablation)Winograd conv protocol · ResNet-18 blockcommunication (GB): 10.45 -> 7.76Improved
naive EWMM Winograd instead of regular conv (ablation)CrypTFlow2 conv · ResNet-18 blockcommunication (GB): 23.74 -> 256Hurt
add Winograd protocol to SNL ResNet-18 (ablation)SNL · CIFAR-100total communication (GB): 61.45 -> 33.84Improved
add Winograd protocol to SNL MobileNetV2 (ablation)SNL · CIFAR-100total communication (GB): 7.710 -> 7.132Improved
add network re-parameterization after pruning (ablation)CoPriv MobileNetV2 · CIFAR-100total communication (GB): 7.806 -> 4.197Improved
add re-parameterization after pruning (ablation)CoPriv MobileNetV2 · CIFAR-100online communication (GB): 0.606 -> 0.331Improved
add Winograd protocol after re-parameterization (ablation)CoPriv MobileNetV2 · CIFAR-100total communication (GB): 4.197 -> 3.154Improved
add Winograd protocol after re-parameterization (ablation)CoPriv MobileNetV2 · CIFAR-100online communication (GB): 0.331 -> 0.331No clear effect
use communication-aware regularization L_comm in pruning (ablation)CoPriv pruning · CIFAR-100 per-block ReLU budgetpruning distributionImproved
CoPriv vs SNL on MobileNetV2-w1.4CoPriv · ImageNetaccuracy and communication: 1.4% higher accuracy, 9.98x online, 3.88x totalImproved
CoPriv vs SNL on ResNet-18CoPriv · CIFAR-100accuracy and communication: 4.3% higher accuracy, 1.55x online, 19.5x totalImproved

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