Strategyproof Learning: Building Trustworthy User-Generated Datasets

by   Sadegh Farhadkhani, et al.

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.


page 1

page 2

page 3

page 4


Random Walks with Erasure: Diversifying Personalized Recommendations on Social and Information Networks

Most existing personalization systems promote items that match a user's ...

Strategic Classification with Graph Neural Networks

Strategic classification studies learning in settings where users can mo...

A Large-Scale Rich Context Query and Recommendation Dataset in Online Knowledge-Sharing

Data plays a vital role in machine learning studies. In the research of ...

Recommending Users: Whom to Follow on Federated Social Networks

To foster an active and engaged community, social networks employ recomm...

Linear Speedup in Personalized Collaborative Learning

Personalization in federated learning can improve the accuracy of a mode...

Incentive design for learning in user-recommendation systems with time-varying states

We consider the problem of how strategic users with asymmetric informati...

Recommending Insurance products by using Users' Sentiments

In today's tech-savvy world every industry is trying to formulate method...