| 本文已被：浏览 6087次 下载 7551次 |
码上扫一扫！ |
|
|
| 带学习的同步隐私保护频繁模式挖掘 |
|
郭宇红1,2, 童云海2, 唐世渭2, 吴冷冬3
|
|
1.国际关系学院 信息科技系,北京 100091;2.北京大学 机器感知与智能教育部重点实验室,北京 100871;3.Department of Computing Science, University of Alberta, Edmonton T6G 2R3, Canada
|
|
| 摘要: |
| 为了提高挖掘结果的准确性,提出基于样例学习和项集同步随机化的隐私保护频繁模式挖掘方法(learning and synchronized privacy preserving frequent pattern mining,简称LS-PPFM).该方法充分利用不需要隐私保护的个体数据,首先对不需要保护的数据学习,得到样例数据中蕴涵的强关联项,然后在对数据随机化时,将强关联项绑定在一起作同步随机化变换,以保持项与项之间的潜在关联性.实验结果表明,相对于项独立随机化,LS-PPFM 能够在略微牺牲一定的隐私保护性的情况下,显著提高频繁模式挖掘结果的准确性. |
| 关键词: 有指导的 基于学习的 随机化 隐私保护 频繁模式挖掘 |
| DOI：10.3724/SP.J.1001.2011.04000 |
| 分类号: |
| 基金项目:国家自然科学基金(60403041, 60473072) |
|
| Learning and Synchronized Privacy Preserving Frequent Pattern Mining |
|
GUO Yu-Hong1,2, TONG Yun-Hai2, TANG Shi-Wei2, WU Leng-Dong3
|
|
1.Department of Information Technology, University of International Relations, Beijing 100091, China;2.Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing 100871, China;3.Department of Computing Science, University of Alberta, Edmonton T6G 2R3, Canada
|
| Abstract: |
| To improve the accuracy of mining results, this paper proposes a method of privacy preserving frequent pattern mining, based on sample learning and synchronized randomization of itemset (LS-PPFM). The method utilizes the data of individuals who do not care privacy. First, the data that does not need protecting are learned, and some strongly associated items are obtained. Then, when the data is randomized, the associated items are bound together and randomized synchronously to try to keep their potential associations. Experimental results show that compared with independent randomization, LS-PPFM can achieve significant improvements on accuracy, while losing a little privacy. |
| Key words: supervised learning-based randomization privacy preserving frequent pattern mining |
