Research map / Federated learning and privacy / Differential privacy
Topological Federated Clustering via Gravitational Potential Fields Under Local Differential Privacy
Yunbo Long, Jiaquan Zhang, Xi Chen, Alexandra Brintrup
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 |
|---|---|---|---|
| use GFC instead of K-Fed/MUFC/NNFC under strong LDP | federated clustering · Gesture (eps=0.01) | ARI: 1.01 -> 8.82 | Improved |
| use GFC instead of baselines under strong LDP | federated clustering · Abalone (eps=0.01) | ARI: 2.92 -> 7.82 | Improved |
| use GFC vs MUFC at eps=0.1 | federated clustering · Waveform (eps=0.1) | ARI: 33.80 -> 23.8 | Hurt |
| use GFC vs K-Fed at eps=0.1 | federated clustering · Thyroid (eps=0.1) | ARI: 43.39 vs 43.38 | No clear effect |
| increase synthetic data multiplier from 1x to 10x at eps=1000 (ablation) | GFC · synthetic data ablation | ARI: 0.82 -> 0.88 -> 0.86 -> 0.37 | Mixed |
| increase synthetic data multiplier from 1x to 10x at eps=0.01 (ablation) | GFC · synthetic data ablation | ARI: 0.10 -> 0.53 | Improved |
| use GFC vs K-Fed runtime | GFC · Abalone | runtime: within 5% time difference | No clear effect |
Closest papers by meaning
- OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance Reconstruction (NeurIPS 2025 · similarity 0.90)
- Differentially Private Federated $k$-Means Clustering with Server-Side Data (ICML 2025 · similarity 0.89)
- Making Old Things New: A Unified Algorithm for Differentially Private Clustering (ICML 2024 · similarity 0.86)
- On the Price of Differential Privacy for Hierarchical Clustering (ICLR 2025 · similarity 0.85)
- Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy (NeurIPS 2025 · similarity 0.85)
- PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectors (NeurIPS 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.
