adversarial-1

Vertical Federated Learning

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in vertical-federated-learning-3

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find vertical-federated-learning-3 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Fedlearn-Algo: A flexible open-source privacy-preserving machine learning platform

Liefeng Bo, Tao Zeng, Peng Dai, Bo Liu, Chaowei Tan, Jiazhou Wang, Huasong Shan, Houpu Yao, Heng Huang, Yanqing Chen•Wed Jul 07 2021

This paper presents Fedlearn-Algo, an open-source privacy preserving machine learning platform, and releases vertical federated kernel binary classification model and vertical Federated random forest model, the first batch of novel FL algorithm examples.

9

Content

0

Paper Graph

Differentially Private Vertical Federated Clustering

Tianhao Wang, Zitao Li, Ninghui Li•Mon Aug 01 2022

The algorithm proposed in this paper is the first practical solution for differentially private vertical federated k -means clustering, where the server can obtain a set of global centers with a provable differential privacy guarantee and improves the estimation accuracy in the setting with more than two data parties.

25 0

Paper Graph

Human–Machine Hybrid Federated Learning: Concept and Applications

Qianru Wang, Qingyang Li, Jiangtao Cui•Fri Nov 14 2025

Federated learning (FL) has become a state-of-the-art technique for addressing data isolation and privacy problems. However, the traditional FL framework has limitations on lack of labeled data, adaptation to evolving environments and tasks, and insufficient generalization of the global model due to nonindependent and identically distributed (non-IID) data. These issues suggest that incorporating human knowledge and interaction into the FL workflow can be beneficial. Human–machine hybrid intelligence (HI) is an area that human abilities are considered to prompt the usability and robustness of the system by providing human domain knowledge. Combining FL and human–machine HI can fully utilize their benefits and complement each other perfectly. This article presents our vision of the next generation of FL, human–machine hybrid intelligent FL, namely HIFL, and this work first defines the concept of HIFL and proposes three patterns of collaboration for HIFL: 1) local HIFL (LocalHIFL); 2) separate HIFL (SeparateHIFL); and 3) cross HIFL (CrossHIFL). In each pattern, we survey methodologies and techniques that are utilized to address specific problems that occurred after adding human–machine collaboration in FL process. Besides, we exhibit some potential application scenarios, and provide several open challenges and opportunities contained in HIFL. This survey intends to provide a high-level summarization for improving FL by combining human–machine HI, and to motivate interested readers to consider approaches for designing effective FL approaches and ways of intelligence fusion according to their requirements.

0 0

Paper Graph

Interpret Federated Learning with Shapley Values

Guan Wang•Fri May 10 2019

This paper proposes a method to balance the model interpretability and data privacy in vertical Federated Learning by using Shapley values to reveal detailed feature importance for host features and a unified importance value for federated guest features.

98 0

Paper Graph

Feature Inference Attack on Model Predictions in Vertical Federated Learning

B. Ooi, Xinjian Luo, Yuncheng Wu, Xiaokui Xiao•Mon Oct 19 2020

This paper presents several feature inference attack methods to investigate the potential privacy leakages in the model prediction stage of vertical FL and proposes two specific attacks on the logistic regression (LR) and decision tree (DT) models, according to individual prediction output.

275 0

Paper Graph

PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN

Daniele Romanini, A. Hall, Pavlos Papadopoulos, Tom Titcombe, Abbas Ismail, Tudor Cebere, R. Sandmann, Robin Roehm, Michael A. Hoeh•Wed Mar 31 2021

This work introduces PyVertical, a framework supporting vertical federated learning using split neural networks, and presents the training of a simple dual-headed split neural network for a MNIST classification task.

112 0

Paper Graph

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

Qinbin Li, Bingsheng He, Zhaomin Wu•Thu Jun 10 2021

A novel coupled training paradigm, FedSim, that integrates one-to-many linkage into the training process that enables VFL in many real-world applications with fuzzy identifiers and achieves better performance in traditional VFL tasks.

23 0

Paper Graph

Achieving Model Fairness in Vertical Federated Learning

J. Pei, Yong Zhang, Lingyang Chu, Changxin Liu, Zirui Zhou, Yang Shi•Thu Sep 16 2021

This work systematically formulate the problem of training fair models in VFL, and develops an asynchronous gradient coordinate-descent ascent algorithm, where some active data parties perform multiple parallelized local updates per communication round to effectively reduce the number of communication rounds.

16 0

Paper Graph

Graph-Fraudster: Adversarial Attacks on Graph Neural Network-Based Vertical Federated Learning

Shanqing Yu, Jinyin Chen, Guohan Huang, Haibin Zheng, Wenrong Jiang, Chen Cui•Tue Oct 12 2021

A novel adversarial attack method, named Graph-Fraudster, which generates adversarial perturbations based on the noise-added global node embeddings via the privacy leakage and the gradient of pairwise node that can remain a threat to GVFL even if two possible defense mechanisms are applied.

39 0

Paper Graph

Adding a benchmark result helps the community track progress.