VFL Algorithm

Vertical Federated Learning (VFL) is a machine learning paradigm enabling collaborative model training across multiple parties holding disjoint features of the same data samples, without directly sharing raw data. Current research emphasizes improving VFL's efficiency and security, focusing on techniques like homomorphic encryption, efficient matrix multiplication methods, and novel algorithms to mitigate backdoor attacks and handle unreliable connectivity or straggler clients. These advancements are crucial for enabling secure and practical applications of VFL in sensitive domains like healthcare and finance, where data privacy is paramount.

Papers

October 2, 2024

A Novel Framework of Horizontal-Vertical Hybrid Federated Learning for EdgeIoT
Kai Li, Yilei Liang, Xin Yuan, Wei Ni, Jon Crowcroft, Chau Yuen, Ozgur B. Akan
Loss Function Vertical Federated Learning Novel Framework Mobile Edge VFL Algorithm Lateral Flow

August 28, 2024

VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification
Yungi Cho, Woorim Han, Miseon Yu, Younghan Lee, Ho Bae, Yunheung Paek
Backdoor Attack Person Identification Vertical Federated Learning Backdoor Defense VFL Algorithm Horizontal Federated Learning

May 1, 2024

PackVFL: Efficient HE Packing for Vertical Federated Learning
Liu Yang, Shuowei Cai, Di Chai, Junxue Zhang, Han Tian, Yilun Jin, Kun Guo, Kai Chen, Qiang Yang
Homomorphic Encryption Vertical Federated Learning Matrix Multiplication VFL Algorithm

October 15, 2023

VFLAIR: A Research Library and Benchmark for Vertical Federated Learning
Tianyuan Zou, Zixuan Gu, Yu He, Hideaki Takahashi, Yang Liu, Ya-Qin Zhang
New Benchmark Vertical Federated Learning Collaborative Training VFL Algorithm

May 26, 2023

Secure Vertical Federated Learning Under Unreliable Connectivity
Xinchi Qiu, Heng Pan, Wanru Zhao, Yan Gao, Pedro P. B. Gusmao, William F. Shen, Chenyang Ma, Nicholas D. Lane
Homomorphic Encryption Vertical Federated Learning VFL Algorithm

May 3, 2023

LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning
Timothy Castiglia, Yi Zhou, Shiqiang Wang, Swanand Kadhe, Nathalie Baracaldo, Stacy Patterson
Feature Selection Vertical Federated Learning Local Feature Communication Efficient Local Datasets VFL Algorithm Feature Set

April 26, 2023

FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models
Songze Li, Duanyi Yao, Jin Liu
Vertical Federated Learning Model Privacy Secret Sharing Model Splitting VFL Algorithm Information Theoretic Privacy

July 20, 2022

Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM
Chulin Xie, Pin-Yu Chen, Qinbin Li, Arash Nourian, Ce Zhang, Bo Li
Differential Privacy Vertical Federated Learning Communication Efficiency Alternating Direction Method of Multiplier VFL Algorithm

June 16, 2022

Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data
Timothy Castiglia, Anirban Das, Shiqiang Wang, Stacy Patterson
Federated Learning Compression Technique Communication Efficient Communication Compression Partitioned Data Top K Sparsification VFL Algorithm

March 19, 2022

Desirable Companion for Vertical Federated Learning: New Zeroth-Order Gradient Based Algorithm
Qingsong Zhang, Bin Gu, Zhiyuan Dang, Cheng Deng, Heng Huang
Vertical Federated Learning Zeroth Order VFL Algorithm Deep Companion

November 5, 2021

DVFL: A Vertical Federated Learning Method for Dynamic Data
Yuzhi Liang, Yixiang Chen
Knowledge Distillation Vertical Federated Learning Privacy Preserving Machine Learning Decentralized Manner Dynamic Information VFL Algorithm

VFL Algorithm

Papers

A Novel Framework of Horizontal-Vertical Hybrid Federated Learning for EdgeIoT

VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification

PackVFL: Efficient HE Packing for Vertical Federated Learning

VFLAIR: A Research Library and Benchmark for Vertical Federated Learning

Secure Vertical Federated Learning Under Unreliable Connectivity

LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning

FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models

Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM

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

Desirable Companion for Vertical Federated Learning: New Zeroth-Order Gradient Based Algorithm

DVFL: A Vertical Federated Learning Method for Dynamic Data