Exploiting Record Similarity for Practical Vertical Federated Learning

06/11/2021
by   Zhaomin Wu, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/13/2022

Practical Vertical Federated Learning with Unsupervised Representation Learning

As societal concerns on data privacy recently increase, we have witnesse...
research
06/18/2021

A Vertical Federated Learning Framework for Horizontally Partitioned Labels

Vertical federated learning is a collaborative machine learning framewor...
research
06/03/2019

Federated Hierarchical Hybrid Networks for Clickbait Detection

Online media outlets adopt clickbait techniques to lure readers to click...
research
03/11/2018

Entity Resolution and Federated Learning get a Federated Resolution

Consider two data providers, each maintaining records of different featu...
research
06/16/2022

BlindFL: Vertical Federated Machine Learning without Peeking into Your Data

Due to the rising concerns on privacy protection, how to build machine l...
research
08/16/2021

Aegis: A Trusted, Automatic and Accurate Verification Framework for Vertical Federated Learning

Vertical federated learning (VFL) leverages various privacy-preserving a...
research
11/28/2011

A kernel-based framework for learning graded relations from data

Driven by a large number of potential applications in areas like bioinfo...

Please sign up or login with your details

Forgot password? Click here to reset