Entity Augmentation for Efficient Classification of Vertically Partitioned Data with Limited Overlap

2024-06-25 · Avi Amalanshu, Viswesh Nagaswamy, G. V. S. S. Prudhvi, Yash Sirvi, Debashish Chakravarty

Vertical Federated Learning (VFL) is a machine learning paradigm for learning from vertically partitioned data (i.e. features for each input are distributed across multiple "guest" clients and an aggregating "host" server owns labels) without communicating raw data. Traditionally, VFL involves an "entity resolution" phase where the host identifies and serializes the unique entities known to all guests. This is followed by private set intersection to find common entities, and an "entity alignment" step to ensure all guests are always processing the same entity's data. However, using only data of entities from the intersection means guests discard potentially useful data. Besides, the effect on privacy is dubious and these operations are computationally expensive. We propose a novel approach that eliminates the need for set intersection and entity alignment in categorical tasks. Our Entity Augmentation technique generates meaningful labels for activations sent to the host, regardless of their originating entity, enabling efficient VFL without explicit entity alignment. With limited overlap between training data, this approach performs substantially better (e.g. with 5% overlap, 48.1% vs 69.48% test accuracy on CIFAR-10). In fact, thanks to the regularizing effect, our model performs marginally better even with 100% overlap.

📄 PDF Abstract BibTeX arXiv:2406.17899

Code (0)

등록된 구현이 없습니다.

Tasks

Entity Alignment Entity Resolution Federated LearningVertical Federated Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Privacy-Preserving Asynchronous Federated Learning Algorithms for Multi-Party Vertically Collaborative Learning

2020-08-14 · Bin Gu, An Xu, Zhouyuan Huo, Cheng Deng 외

The privacy-preserving federated learning for vertically partitioned data has shown promising results as the solution of the emerging multi-party joint modeling application, in which the data holders (such as government …

Federated Learning Privacy Preserving

Privacy-preserving Data Sharing on Vertically Partitioned Data

2020-10-19 · Razane Tajeddine, Joonas Jälkö, Samuel Kaski, Antti Honkela

In this work, we introduce a differentially private method for generating synthetic data from vertically partitioned data, \emph{i.e.}, where data of the same individuals is distributed across multiple data holders or pa…

Privacy Preserving Variational Inference

Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data

2022-06-16 · Timothy Castiglia, Anirban Das, Shiqiang Wang, Stacy Patterson

We propose Compressed Vertical Federated Learning (C-VFL) for communication-efficient training on vertically partitioned data. In C-VFL, a server and multiple parties collaboratively train a model on their respective fea…

Federated Learning Quantization Vertical Federated Learning

Achieving Differential Privacy in Vertically Partitioned Multiparty Learning

2019-11-11 · Depeng Xu, Shuhan Yuan, Xintao Wu

Preserving differential privacy has been well studied under centralized setting. However, it's very challenging to preserve differential privacy under multiparty setting, especially for the vertically partitioned case. I…

Privacy Preserving

Federated Doubly Stochastic Kernel Learning for Vertically Partitioned Data

2020-08-14 · Bin Gu, Zhiyuan Dang, Xiang Li, Heng Huang

In a lot of real-world data mining and machine learning applications, data are provided by multiple providers and each maintains private records of different feature sets about common entities. It is challenging to train…

BIG-bench Machine Learning Federated Learning