mlsanityData to 14 Oct 2026

ICAFS: Inter-Client-Aware Feature Selection for Vertical Federated Learning

arXiv 2504.10851 ↗First posted 15 Apr 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Vertical federated learning (VFL) enables a paradigm for vertically partitioned data across clients to collaboratively train machine learning models. Feature selection (FS) plays a crucial role in Vertical Federated Learning (VFL) due to the unique nature that data are distributed across multiple clients. In VFL, different clients possess distinct subsets of features for overlapping data samples, making the process of identifying and selecting the most relevant features a complex yet essential task. Previous FS efforts have primarily revolved around intra-client feature selection, overlooking vital feature interaction across clients, leading to subpar model outcomes. We introduce ICAFS, a novel multi-stage ensemble approach for effective FS in VFL by considering inter-client interactions. By employing conditional feature synthesis alongside multiple learnable feature selectors, ICAFS facilitates ensemble FS over these selectors using synthetic embeddings. This method bypasses the limitations of private gradient sharing and allows for model training using real data with refined embeddings. Experiments on multiple real-world datasets demonstrate that ICAFS surpasses current state-of-the-art methods in prediction accuracy.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 56 references that are in the map. First posted on arXiv 15 Apr 2025.

Builds on

25 of 56 references.

References · 25

  1. 2016Deep Learning with Differential Privacycited by 2,728
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  3. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
  4. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 246
  5. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  6. 2020VAFL: a Method of Vertical Asynchronous Federated Learningcited by 87
  7. 2020Multi-Participant Multi-Class Vertical Federated Learningcited by 47
  8. 2021FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learningcited by 39
  9. 2024Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchorscited by 21
  10. 2017Kernel Feature Selection via Conditional Covariance Minimizationcited by 20
  11. 2021Batch Label Inference and Replacement Attacks in Black-Boxed Vertical Federated Learningcited by 16
  12. 2017Learning with Feature Evolvable Streamscited by 15
13 more
  1. 2023FedSDG-FS: Efficient and Secure Feature Selection for Vertical Federated Learningcited by 15
  2. 2023LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learningcited by 14
  3. 2023Optimizing Feature Set for Click-Through Rate Predictioncited by 13
  4. 2022Composite Feature Selection using Deep Ensemblescited by 11
  5. 2021Fed-EINI: An Efficient and Interpretable Inference Framework for Decision Tree Ensembles in Federated Learningcited by 10
  6. 2019Prediction with Unpredictable Feature Evolutioncited by 8
  7. 2025Synthetic Data Privacy Metricscited by 8
  8. 2024Synthetic Tabular Data Validation: A Divergence-Based Approachcited by 7
  9. 2020High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimationcited by 6
  10. 2023VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarkscited by 6
  11. 2020Storage Fit Learning with Feature Evolvable Streamscited by 5
  12. 2020A Multi-Way Correlation Coefficientcited by 2
  13. 2020A Compound Decision Approach to Covariance Matrix Estimationcited by 1

Built on by

Not cited yet.