Decentralized Multi-Target Cross-Domain Recommendation for Multi-Organization Collaborations

TL;DR

This paper introduces a decentralized recommendation framework enabling multiple organizations to collaboratively improve their recommendation accuracy without sharing sensitive data, addressing privacy concerns and cold start issues.

Contribution

It proposes a novel decentralized multi-target cross-domain recommendation method with MTAL and AAE, facilitating collaboration without data sharing.

Findings

Significantly outperforms local recommendation models

Mitigates cold start problem effectively

Enables privacy-preserving multi-organization collaboration

Abstract

Recommender Systems (RSs) are operated locally by different organizations in many realistic scenarios. If various organizations can fully share their data and perform computation in a centralized manner, they may significantly improve the accuracy of recommendations. However, collaborations among multiple organizations in enhancing the performance of recommendations are primarily limited due to the difficulty of sharing data and models. To address this challenge, we propose Decentralized Multi-Target Cross-Domain Recommendation (DMTCDR) with Multi-Target Assisted Learning (MTAL) and Assisted AutoEncoder (AAE). Our method can help multiple organizations collaboratively improve their recommendation performance in a decentralized manner without sharing sensitive assets. Consequently, it allows decentralized organizations to collaborate and form a community of shared interest. We conduct extensive experiments to demonstrate that the new method can significantly outperform locally trained RSs and mitigate the cold start problem.