• Home
  • Search
  • A Personalized and Privacy-Preserving Federated Transformer Framework for Multilingual Sentiment Analysis.
  • https://doi.org/10.1109/tpami.2026.3663617Copy DOI Icon

A Personalized and Privacy-Preserving Federated Transformer Framework for Multilingual Sentiment Analysis.

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Personalized federated learning for multilingual sentiment analysis poses significant challenges arising from linguistic heterogeneity, non-IID data distributions, and strict privacy requirements. This paper proposes FedPerX, a federated transformer framework that integrates residual adapter-based personalization with adaptive multi-granular differential privacy. The architecture leverages a frozen multilingual backbone (XLM-R) while enabling each client to train lightweight, client-specific adapters. Privacy is enforced through dynamic noise injection at both the feature and adapter levels, calibrated using gradient sensitivity. FedPerX is evaluated on two multilingual benchmarks-MARC and TSMD-spanning structured reviews and informal social media content across more than ten languages. Experimental results demonstrate consistent improvements over seven state-of-the-art baselines, with up to +4.3% gains in macro-F1, a 70% reduction in communication overhead, and the lowest variance in client-level performance. Comprehensive analyses, including fairness, personalization gap, privacy-utility trade-off, and ablation studies, validate the framework's robustness and adaptability. FedPerX advances the design of scalable, personalized, and privacy-preserving models for federated multilingual sentiment analysis.

Similar Papers
  • Research Article

A Privacy-Preserving Authentication Scheme for Federated Learning in Drone-Assisted Vehicular Networks

  • Jan 01, 2025
  • IEEE Transactions on Intelligent Transportation Systems
  • Wenming Wang +8
  • Research Article
  • Citations1

An Implementation of A Parallel Iterative Algorithm for the Solution of Large Banded System on A Cluster of Workstations

  • Jan 01, 2008
  • International Journal of Modelling and Simulation
  • M Al-Towaiq +3
  • Conference Article
  • Citations2

Distributed Diffusion-Based Mesh Algorithm for Distributed Mesh Construction in Wireless Ad Hoc and Sensor Networks

  • May 01, 2010
  • K Egoh +2
  • Conference Article

Computer Vision in the Era of Big Data: A Deep Learning-Based Analytical Perspective

  • Sep 19, 2025
  • R Ruth Shobitha +4
  • Research Article
  • Citations2

Privacy-Preserving Deep Reinforcement Learning for Secure Resource Orchestration in Cyber-Physical Systems

  • Apr 30, 2025
  • International Journal of Scientific Research in Network Security and Communication
  • Manas Kumar Yogi +1
  • Research Article
  • Citations8

A method for exploiting communication/computation overlap in hypercubes

  • Feb 01, 1998
  • Parallel Computing
  • Luis Dı́Az De Cerio +2
  • Abstract
  • Citations8

Database requirements of engineering applications/an analysis: Peter, C. Lockemann, Klaus R. Dittrich, Marcus Adams, Martin Bever, Barbara Ferkinghoff, Willi Gotthard, Angelika M. Kotz, Rolf-Peter Liedtke, Birgit Lueke and Jutta A. Muelle, Interner Bericht 12/85, Universitaet Karlsruhe, FPI, 7500 Karlsruhe, West Germany, 1985.

  • Sep 01, 1986
  • Decision Support Systems
  • Research Article
  • Citations29

Federated Learning-Driven Cybersecurity Framework for IoT Networks with Privacy Preserving and Real-Time Threat Detection Capabilities

  • Jul 04, 2025
  • Informatics
  • Milad Rahmati +1
  • Research Article
  • Citations26

A multi-aspect framework for explainable sentiment analysis

  • Jan 07, 2024
  • Pattern Recognition Letters
  • Jothi Prakash V +1
  • Research Article
  • Citations2

An improved blockchain-based multi-region Federated Learning framework for crop disease diagnosis

  • Apr 01, 2025
  • Computers and Electrical Engineering
  • Yuanze Qin +4
  • Research Article
  • Citations30

Secure Decentralized Image Classification With Multiparty Homomorphic Encryption

  • Jul 01, 2023
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Guowen Xu +4
  • Book Chapter
  • Citations5

Bandwidth-Optimized Secure Two-Party Computation of Minima

  • Jan 01, 2015
  • Jan Henrik Ziegeldorf +4
  • Book Chapter
  • Citations43

CORBA Components Collocation Optimization Enhanced with Local ORB-Like Services Support

  • Jan 01, 2004
  • Mohsen Sharifi +3
  • Research Article
  • Citations16

Secured lightweight authentication for 6LoWPANs in machine-to-machine communications

  • Jul 14, 2024
  • Computers & Security
  • Fatma Foad Ashrif +5
  • Research Article
  • Citations8

Communication-Efficient Federated Double Distillation in IoV

  • Oct 01, 2023
  • IEEE Transactions on Cognitive Communications and Networking
  • Peng Yang +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.