Research map / Federated learning and privacy / Personalized and heterogeneous FL
Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updating
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add backward updating so passive parties can update their feature blocks using the transmitted loss derivative | VF-B²-SVRG · D1 (UCICreditCard), strongly convex logistic regression | accuracy: 79.35%$\pm$0.19% -> 81.96%$\pm$0.22% | Helped |
| Add backward updating so passive parties can update their feature blocks using the transmitted loss derivative | VF-B²-SVRG · D2 (GiveMeSomeCredit), strongly convex logistic regression | accuracy: 93.35%$\pm$0.18% -> 93.56%$\pm$0.20% | Helped |
| Add backward updating so passive parties can update their feature blocks using the transmitted loss derivative | VF-B²-SVRG · D3 (news20), strongly convex logistic regression | accuracy: 97.24%$\pm$0.11% -> 98.29%$\pm$0.20% | Helped |
| Add backward updating so passive parties can update their feature blocks using the transmitted loss derivative | VF-B²-SVRG · D4 (webspam), strongly convex logistic regression | accuracy: 89.17%$\pm$0.10% -> 92.17%$\pm$0.13% | Helped |
| Add backward updating so passive parties can update their feature blocks using the transmitted loss derivative | VF-B²-SVRG · D1–D4, nonconvex logistic regression | accuracy | Helped |
| Use backward updating with asynchronous rather than synchronous execution | VF-B²-SGD, VF-B²-SVRG, and VF-B²-SAGA · Classification and regression experiments | time to reach a given loss | Helped |
| Use variance reduction (SVRG or SAGA) rather than SGD | VF-B² algorithms · Classification experiments | convergence rate over epochs | Helped |
Closest papers by meaning
- A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs (NeurIPS 2024 · similarity 0.88)
- Integer Is Enough: When Vertical Federated Learning Meets Rounding (AAAI 2024 · similarity 0.86)
- PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture (NeurIPS 2025 · similarity 0.86)
- Complementary Knowledge Distillation for Robust and Privacy-Preserving Model Serving in Vertical Federated Learning (AAAI 2024 · similarity 0.86)
- VFLAIR: A Research Library and Benchmark for Vertical Federated Learning (ICLR 2024 · similarity 0.85)
- Towards Trustworthy Federated Learning with Untrusted Participants (ICML 2025 · similarity 0.85)
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.