Research map / Federated learning and privacy / Differential privacy
Federated Latent Dirichlet Allocation: A Local Differential Privacy Based Framework
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 |
|---|---|---|---|
| train LDA with FedLDA local DP (eps=7.5) instead of centralized no-privacy LDA | LDA · Spam filtering | AUC: 0.798 -> 0.771 | Hurt |
| tighter privacy budget eps=5.0 instead of 7.5 (ablation) | FedLDA · Spam filtering | AUC: 0.771 -> 0.738 | Hurt |
| train LDA with FedLDA local DP (eps=7.5) | LDA · Sentiment analysis | AUC: 0.794 -> 0.778 | Hurt |
| increase privacy budget epsilon (ablation) | FedLDA and baselines · Reviews/Emails | perplexity | Helped |
| RRP perturbation instead of t-kRR baseline | FedLDA · Reviews/Emails | perplexity | Helped |
| increase failure probability delta (ablation) | RRP · Reviews/Emails | perplexity | No clear effect |
| increase sample ratio l/M (ablation) | FedLDA · Reviews/Emails | perplexity | Helped |
Closest papers by meaning
- Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy (NeurIPS 2025 · similarity 0.86)
- Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix (NeurIPS 2025 · similarity 0.86)
- Little Is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning (AAAI 2025 · similarity 0.85)
- Synthesizing Privacy-Preserving Text Data via Finetuning *without* Finetuning Billion-Scale LLMs (ICML 2025 · similarity 0.85)
- Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning (ICML 2024 · similarity 0.85)
- DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing (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.