.png){kind=icon}
返回
Coded Machine Unlearning
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2021.3090019.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
There are applications that may require removing the trace of a sample from the system, e.g., a user requests their data to be deleted, or corrupted data is discovered. Simply removing a sample from storage units does not necessarily remove its entire trace since downstream machine learning models may store some information about the samples used to train them. A sample can be perfectly unlearned if we retrain all models that used it from scratch with that sample removed from their training dataset. When multiple such unlearning requests are expected to be served, unlearning by retraining becomes prohibitively expensive. Ensemble learning enables the training data to be split into smaller disjoint shards that are assigned to non-communicating weak learners. Each shard is used to produce a weak model. These models are then aggregated to produce the final central model. This setup introduces an inherent trade-off between performance and unlearning cost, as reducing the shard size reduces the unlearning cost but may cause degradation in performance. In this paper, we propose a coded learning protocol where we utilize linear encoders to encode the training data into shards prior to the learning phase. We also present the corresponding unlearning protocol and show that it satisfies the perfect unlearning criterion. Our experimental results show that the proposed coded machine unlearning provides a better performance versus unlearning cost trade-off compared to the uncoded baseline.
Keyword:
Training
Protocols
Kernel
Machine learning
Encoding
Predictive models
Licenses
Machine unlearning
random coding
efficient sample removal
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
Normative pediatric visual acuity using single surrounded HOTV optotypes on the Electronic Visual Acuity Tester following the Amblyopia Treatment Study protocol根据弱视治疗研究方案，在电子视力测试仪上使用单个包围的HOTV视标的儿童视力OAAI
OAAI分享收藏NPMML: A Framework for Non-Interactive Privacy-Preserving Multi-Party Machine LearningNPMML: 一种非交互式隐私保护多方机器学习框架
PREAI
分享收藏Catalytic activity of dihydride ruthenium complexes in the hydrogenation of nitrogen containing heterocycles二氢化物钌配合物在含氮杂环氢化中的催化活性
PREAI
分享收藏Developing Wind and/or Solar Powered Crop Irrigation Systems for the Great Plains为大平原开发风能和/或太阳能作物灌溉系统
PREAI
分享收藏
查看更多内容