Projected Federated Averaging with Heterogeneous Differential Privacy
Summary: Introduces PFA for federated learning with heterogeneous differential privacy, projecting private updates onto the top singular subspace from public clients before aggregation. PFA+ enables uploading projected updates, achieving over 99% uplink reduction with preserved utility. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Junxu Liu
- 2. Jian Lou
- 3. Li Xiong
- 4. Jinfei Liu
- 5. Xiaofeng Meng
Incoming Citations (Sorted by Pagerank)
Showing 7 of 7 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 6,502 | Falcon: A Privacy-Preserving and Interpretable Vertical Federated Learning System | 2023 | VLDB | 5.0361846e-05 |
| 7,484 | Privacy Amplification via Shuffling: Unified, Simplified, and Tightened | 2024 | VLDB | 4.7180617e-05 |
| 8,459 | Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs | 2024 | VLDB | 4.5065275e-05 |
| 9,150 | Infinite Stream Estimation under Personalized w-Event Privacy | 2025 | VLDB | 4.3849295e-05 |
| 9,323 | FEAST: A Communication-efficient Federated Feature Selection Framework for Relational Data | 2023 | SIGMOD | 4.3556432e-05 |
| 10,664 | Calibrating Noise for Group Privacy in Subsampled Mechanisms | 2025 | VLDB | 4.1945683e-05 |
| 10,978 | A Profit-Maximizing Data Marketplace with Differentially Private Federated Learning under Price Competition | 2024 | SIGMOD | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 0 of 0 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next