As an emerging secure learning paradigm in leveraging cross-agency private data, vertical federated learning (VFL) is expected to improve advertising models by enabling the joint learning of complementary user attributes privately owned by the advertiser and the publisher. However, there are two key challenges in applying it to advertising systems: a) the limited scale of labeled overlapping samples, and b) the high cost of real-time cross-agency serving. In this paper, we propose a semi-supervised split distillation framework VFed-SSD to alleviate the two limitations. We identify that: i) there are massive unlabeled overlapped data available in advertising systems, and ii) we can keep a balance between model performance and inference cost by decomposing the federated model. Specifically, we develop a self-supervised task Matched Pair Detection (MPD) to exploit the vertically partitioned unlabeled data and propose the Split Knowledge Distillation (SplitKD) schema to avoid cross-agency serving. Empirical studies on three industrial datasets exhibit the effectiveness of our methods, with the median AUC over all datasets improved by 0.86% and 2.6% in the local deployment mode and the federated deployment mode respectively. Overall, our framework provides an efficient federation-enhanced solution for real-time display advertising with minimal deploying cost and significant performance lift.

本文提出了一个名为VFed-SSD的半监督分裂蒸馏框架，通过匹配对检测（MPD）的自监督任务和避免跨机构服务的Split Knowledge Distillation（SpiltKD）模式来克服在广告系统中应用垂直联邦学习的两个挑战：标记样本缺乏和实时跨机构服务成本高。实证研究表明，我们的方法在三个工业数据集上表现良好，平均AUC分别提高了0.86％和2.6％，在本地部署模式和联邦部署模式下都显著提高了效果。

自监督分割蒸馏实现轻量化联合广告