FedUD: Exploiting Unaligned Data for Cross-Platform Federated Click-Through Rate Prediction

TL;DR

FedUD introduces a novel federated learning approach that leverages both aligned and unaligned user data across platforms to improve click-through rate prediction while preserving privacy.

Contribution

The paper proposes FedUD, a method that exploits unaligned data in federated learning for CTR prediction, extending traditional VFL capabilities.

Findings

FedUD outperforms existing methods on real-world datasets.

Incorporating unaligned data improves CTR prediction accuracy.

Knowledge distillation enhances representation transfer in federated learning.

Abstract

Click-through rate (CTR) prediction plays an important role in online advertising platforms. Most existing methods use data from the advertising platform itself for CTR prediction. As user behaviors also exist on many other platforms, e.g., media platforms, it is beneficial to further exploit such complementary information for better modeling user interest and for improving CTR prediction performance. However, due to privacy concerns, data from different platforms cannot be uploaded to a server for centralized model training. Vertical federated learning (VFL) provides a possible solution which is able to keep the raw data on respective participating parties and learn a collaborative model in a privacy-preserving way. However, traditional VFL methods only utilize aligned data with common keys across parties, which strongly restricts their application scope. In this paper, we propose FedUD, which is able to exploit unaligned data, in addition to aligned data, for more accurate federated CTR prediction. FedUD contains two steps. In the first step, FedUD utilizes aligned data across parties like traditional VFL, but it additionally includes a knowledge distillation module. This module distills useful knowledge from the guest party's high-level representations and guides the learning of a representation transfer network. In the second step, FedUD applies the learned knowledge to enrich the representations of the host party's unaligned data such that both aligned and unaligned data can contribute to federated model training. Experiments on two real-world datasets demonstrate the superior performance of FedUD for federated CTR prediction.