Federated Calibration and Evaluation of Binary Classifiers
Summary: Protocols for calibrating binary classifier scores and computing precision/recall/accuracy/ROC‑AUC in federated settings without centralizing labels, supporting secure aggregation, distributed DP, and local DP. Theorems and experiments quantify privacy–utility–data‑efficiency tradeoffs and provide practical criteria to decide when federated calibration/evaluation is viable. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Graham Cormode
- 2. Igor L. Markov
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,368 | Answering Multi-Dimensional Range Queries under Local Differential Privacy | 2021 | VLDB | 7.1714763e-05 |
| 3,399 | Answering Range Queries Under Local Differential Privacy | 2019 | VLDB | 7.1408089e-05 |
Previous
Page 1 / 1
Next