A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learning

Abstract

As the privacy of machine learning has drawn increasing attention, federated learning is introduced to enable collaborative learning without revealing raw data. Notably, vertical federated learning (VFL), where parties share the same set of samples but only hold partial features, has a wide range of real-world applications. However, existing studies in VFL rarely study the "record linkage" process. They either design algorithms assuming the data from different parties have been linked or use simple linkage methods like exact-linkage or top1-linkage. These approaches are unsuitable for many applications, such as the GPS location and noisy titles requiring fuzzy matching. In this paper, we design a novel similarity-based VFL framework, FedSim, which is suitable for more real-world applications and achieves higher performance on traditional VFL tasks. Moreover, we theoretically analyze the privacy risk caused by sharing similarities. Our experiments on three synthetic datasets and five real-world datasets with various similarity metrics show that FedSim consistently outperforms other state-of-the-art baselines.Preprint. Under review.

Task-Driven Transferred Vertical Federated Deep Learning for Multivariate Internet of Things Time-Series Analysis

“…In other words, TT-VFDL-SIM and DT-VFDL-AE do not need to consider data alignment between each guest party during partial task training. On the other hand, existing VFDL methods of the training loop parallelization approach, such as P-VFDL-SL, must align the raw data of each guest party [44][45][46]. TT-VFDL-SIM leverages a transfer learning mechanism to enable distributed learning with improved performance while being independent of data alignment issues between guest parties.…”

A Review on Intelligent Energy Management Systems for Future Electric Vehicle Transportation

“…On the other hand, in scenarios where similar data samples share different feature scopes, Vertical Federated Learning or feature-based FL is applicable [68]. For instance, an insurance company and a car-rental company datasets may likely include similar users residing in an area; therefore, the two companies' sample ID spaces may have a large intersection, however, their feature spaces differ [69]. In order to use both parties' data to process a computation, we need to build a model to collaboratively aggregate different features for similar samples.…”