Papers › Fine-grained Private Knowledge Distillation
Fine-grained Private Knowledge Distillation
Yuntong Li, Shaowei Wang, Yingying Wang, Jin Li, Yuqiu Qian, Bangzhou Xin, Wei Yang
The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.
Knowledge distillation has emerged as a scalable and effective way for privacy-preserving machine learning. One remaining drawback is that it consumes privacy in a model-level (i.e., client-level) manner, every distillation query incurs privacy loss of one client's all records. In order to attain fine-grained privacy accountant and improve utility, this work proposes a model-free reverse k-NN labeling method towards record-level private knowledge distillation, where each record is employed for labeling at most k queries. Theoretically, we provide bounds of labeling error rate under the centralized/local/shuffle model of differential privacy (w.r.t. the number of records per query, privacy budgets). Experimentally, we demonstrate that it achieves new state-of-the-art accuracy with one order of magnitude lower of privacy loss. Specifically, on the CIFAR-$10$ dataset, it reaches 82.1% test accuracy with centralized privacy budget $1.0$; on the MNIST/SVHN dataset, it reaches 99.1%/95.6% accuracy respectively with budget $0.1$. It is the first time deep learning with differential privacy achieve comparable accuracy with reasonable data privacy protection (i.e., exp(ϵ)≤1.5). Our code is available at https://github.com/liyuntong9/rknn.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections