Research map / Federated learning and privacy / Personalized and heterogeneous FL
A Unified Solution for Privacy and Communication Efficiency in Vertical Federated Learning
Ganyu Wang, Bin Gu, Qingsong Zhang, Xiang Li, Boyu Wang, Charles Ling
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace first-order backward messages with ZOO (AvgRand-100) (ablation) | VFL-CZOFO · dist-MNIST | test accuracy: 97.36 -> 95.30 | Hurt |
| replace first-order backward messages with ZOO (AvgRand-100) (ablation) | VFL-CZOFO · dist-MNIST | backward cost: 3073 MB -> 75 MB | Improved |
| decrease ZOO sampling count q from 100 to 10 (ablation) | AvgRand ZOO · dist-MNIST | test accuracy: 95.30 -> 93.33 | Hurt |
| decrease ZOO sampling count q from 10 to 1 (ablation) | AvgRand ZOO · dist-MNIST | test accuracy: 93.33 -> 79.66 | Hurt |
| increase sampling count q (ablation) | VFL-CZOFO · dist-MNIST | convergence speed | Improved |
| compress forward message to 8 bits (ablation) | AvgRand-100 · dist-MNIST | test accuracy: 95.30 -> 95.02 | No clear effect |
| compress forward message to 4 bits (ablation) | AvgRand-100 · dist-MNIST | test accuracy: 95.30 -> 93.35 | Hurt |
| compress forward message to 2 bits (ablation) | AvgRand-100 · dist-MNIST | test accuracy: 95.30 -> 79.10 | Hurt |
| compress forward message to 1 bit (ablation) | AvgRand-100 · dist-MNIST | test accuracy: 95.30 -> 30.20 | Hurt |
| compress backward message to 8 bits (ablation) | AvgRand-100 · dist-MNIST | test accuracy: 95.30 -> 94.58 | No clear effect |
| compress backward message to 2 bits (ablation) | AvgRand-100 · dist-MNIST | test accuracy: 95.30 -> 94.16 | No clear effect |
| compress backward message to 1 bit (ablation) | AvgRand-100 · dist-MNIST | test accuracy: 95.30 -> 90.67 | Hurt |
Closest papers by meaning
- VFLAIR: A Research Library and Benchmark for Vertical Federated Learning (ICLR 2024 · similarity 0.88)
- PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture (NeurIPS 2025 · similarity 0.87)
- Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization (ICLR 2025 · similarity 0.87)
- Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off (ICML 2025 · similarity 0.87)
- Sketched Gaussian Mechanism for Private Federated Learning (NeurIPS 2025 · similarity 0.87)
- Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems (ICML 2024 · similarity 0.87)
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.
