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 2210.02450cs.LGcs.AI
收藏

基于最大熵模型的聚合数据学习

Learning from aggregated data with a maximum entropy model

Criteo(科韬广告)

Alexandre Gilotte, Ahmed Ben Yahmed, David Rohde

摘要:

聚合数据集,然后注入一些噪声,是一种简单而常见的方法来释放差异隐私数据。然而,聚合数据-即使没有噪声-也不是机器学习分类器的合适输入。在这项工作中,我们展示了一个新的模型,类似于逻辑回归,可以从聚合数据中学习,只通过近似未观察到的特征分布与最大熵假设。由此产生的模型是马尔可夫随机场(MRF),我们详细介绍了如何应用,修改和扩展MRF训练算法到我们的设置。最后,我们在几个公共数据集上提出了经验证据,证明以这种方式学习的模型可以实现与使用完整未聚合数据训练的逻辑模型相当的性能。

英文摘要:

Aggregating a dataset, then injecting some noise, is a simple and common way to release differentially private data.However, aggregated data -- even without noise -- is not an appropriate input for machine learning classifiers.In this work, we show how a new model, similar to a logistic regression, may be learned from aggregated data only by approximating the unobserved feature distribution with a maximum entropy hypothesis. The resulting model is a Markov Random Field (MRF), and we detail how to apply, modify and scale a MRF training algorithm to our setting. Finally we present empirical evidence on several public datasets that the model learned this way can achieve performances comparable to those of a logistic model trained with the full unaggregated data.

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。

↑