arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1207.3269cs.LGcs.ITmath.IT
收藏

不可信推荐引擎中隐私的代价

The Price of Privacy in Untrusted Recommendation Engines

Stanford University(斯坦福大学);Technicolor(特艺集团);Microsoft Research - INRIA Joint Center(微软研究院-法国国家信息与自动化研究所联合中心)

Siddhartha Banerjee, Nidhi Hegde, Laurent Massoulié

摘要:

最近在线隐私问题的增加引发了以下问题:如果用户不将其私人数据委托给推荐系统,那么推荐系统是否准确?为了回答这个问题,我们研究了学习项目集群下的本地差分隐私,一个强大的,正式的数据隐私的概念。我们开发的样本的学习项目集群从私有化的用户输入的复杂性的界限。值得注意的是,我们的研究结果确定了在信息丰富和信息稀缺的制度学习之间的样本复杂性分离,从而突出了隐私和每个用户可用的信息量(评级)之间的相互作用。在信息丰富的制度,其中每个用户率至少一个恒定的分数的项目,谱聚类方法,以实现一个简单的信息理论参数的基础上法诺不等式的样本复杂性下界。然而,信息稀缺的制度,其中每个用户率只有一个消失的部分项目,发现需要一个根本不同的方法都为下限和算法。为此,我们开发了新的技术有界互信息下的信道失配的概念,并提出了一种新的算法,MaxSense,并表明,它实现了最佳的样本复杂度在这种情况下。我们开发的用于限定互信息的技术可能具有更广泛的意义。为了说明这一点,我们展示了它们对基于1位草图的$(i)$学习和$(ii)$自适应学习的适用性,其中查询可以根据过去查询的答案进行调整。

英文摘要:

Recent increase in online privacy concerns prompts the following question: can a recommender system be accurate if users do not entrust it with their private data? To answer this, we study the problem of learning item-clusters under local differential privacy, a powerful, formal notion of data privacy. We develop bounds on the sample-complexity of learning item-clusters from privatized user inputs. Significantly, our results identify a sample-complexity separation between learning in an information-rich and an information-scarce regime, thereby highlighting the interaction between privacy and the amount of information (ratings) available to each user. In the information-rich regime, where each user rates at least a constant fraction of items, a spectral clustering approach is shown to achieve a sample-complexity lower bound derived from a simple information-theoretic argument based on Fano's inequality. However, the information-scarce regime, where each user rates only a vanishing fraction of items, is found to require a fundamentally different approach both for lower bounds and algorithms. To this end, we develop new techniques for bounding mutual information under a notion of channel-mismatch, and also propose a new algorithm, MaxSense, and show that it achieves optimal sample-complexity in this setting. The techniques we develop for bounding mutual information may be of broader interest. To illustrate this, we show their applicability to $(i)$ learning based on 1-bit sketches, and $(ii)$ adaptive learning, where queries can be adapted based on answers to past queries.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑