Today's large-scale machine learning algorithms harness massive amounts of user-generated data to train large models. However, especially in the context of content recommendation with enormous social, economical and political incentives to promote specific views, products or ideologies, strategic users might be tempted to fabricate or mislabel data in order to bias algorithms in their favor. Unfortunately, today's learning schemes strongly incentivize such strategic data misreporting. This is a major concern, as it endangers the trustworthiness of the entire training datasets, and questions the safety of any algorithm trained on such datasets. In this paper, we show that, perhaps surprisingly, incentivizing data misreporting is not a fatality. We propose the first personalized collaborative learning framework, Licchavi, with provable strategyproofness guarantees through a careful design of the underlying loss function. Interestingly, we also prove that Licchavi is Byzantine resilient: it tolerates a minority of users that provide arbitrary data.
翻译:今天的大型机器学习算法利用大量用户生成的数据来训练大型模型。 但是,特别是在内容建议方面,在具有巨大的社会、经济和政治激励因素以促进特定观点、产品或意识形态的情况下,战略用户可能会试图编造或错误标签数据,以便偏向于算法。 不幸的是,今天的学习计划强烈激励了这种战略数据误报。这是一个重大关切问题,因为它危及整个培训数据集的可信赖性,并质疑任何在这类数据集方面受过培训的算法的安全性。在本文中,我们表明,也许令人惊讶的是,激励数据误报并不是致命的。我们提出了第一个个性化的协作学习框架,即Licchavi,通过仔细设计基本损失功能来保证战略的可逆性。有趣的是,我们还证明了Licchavi具有拜占庭的复原力:它容忍少数提供任意数据的用户。