Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
8.3
3.6
Journals
Future Internet
Special Issues
Federated Learning: Challenges, Methods, and Future Directions
share announcement

Federated Learning: Challenges, Methods, and Future Directions

A special issue of Future Internet (ISSN 1999-5903). This special issue belongs to the section "Internet of Things".

Deadline for manuscript submissions: 31 July 2026 | Viewed by 1401

Special Issue Editors

Dr. Naiyue Chen

E-Mail Website
Guest Editor
School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China
Interests: computer technology; software engineering; artificial intelligence; big data technology and engineering; machine learning and cognitive computing; data and knowledge engineering; new generation electronic information technology
Dr. Ivan Serina

E-Mail Website
Guest Editor
Department of Information Engineering, University of Brescia, Via Branze 38, 25121 Brescia, Italy
Interests: artificial intelligence; AI planning; multi-agent planning; machine learning; neural networks; deep learning; heuristic optimization; heuristic search
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Federated Learning (FL) has emerged as a transformative decentralized machine learning paradigm, enabling collaborative model training across distributed devices while rigorously preserving data privacy. This Special Issue delves into the critical challenges, innovative methodologies, and future prospects of FL, focusing on core issues such as data heterogeneity, communication efficiency, privacy preservation, and security threats. Featured contributions present cutting-edge techniques, including efficient model aggregation, robustness enhancement, and differential privacy mechanisms, to advance FL performance.

This Special Issue examines FL’s practical applications in domains including healthcare, IoT, and edge computing, emphasizing scalability and fairness in real-world deployments. It also highlights promising research directions, such as improving algorithmic robustness and fairness, reducing computational overhead, and integrating FL with emerging technologies such as blockchain and 6G networks.

By curating state-of-the-art research, this Special Issue supports FL as a scalable, efficient, and privacy-preserving cornerstone for next-generation AI systems.

Dr. Naiyue Chen
Dr. Ivan Serina
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Future Internet is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • federated learning
  • decentralized machine learning
  • IoT
  • edge computing
  • blockchain
  • 6G network
  • data heterogeneity

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

18 pages, 5351 KB  
Article
Dual-Factor Adaptive Robust Aggregation for Secure Federated Learning in IoT Networks
by Zuan Song, Wuzheng Tan, Hailong Wang, Guilong Zhang and Jian Weng
Future Internet 2026, 18(4), 201; https://doi.org/10.3390/fi18040201 - 10 Apr 2026
Viewed by 300
Abstract
Federated Learning (FL) has been widely adopted in privacy-sensitive and distributed environments. However, training stability becomes significantly challenged when differential privacy (DP) noise and Byzantine client behaviors coexist, as these heterogeneous perturbations jointly introduce time-varying distortions to model updates. Existing approaches typically address [...] Read more.
Federated Learning (FL) has been widely adopted in privacy-sensitive and distributed environments. However, training stability becomes significantly challenged when differential privacy (DP) noise and Byzantine client behaviors coexist, as these heterogeneous perturbations jointly introduce time-varying distortions to model updates. Existing approaches typically address privacy and robustness in isolation. Under DP constraints, noise injection increases gradient variance and obscures the distinction between benign and adversarial updates, causing many robust aggregation methods to misclassify normal clients or fail to detect malicious ones. As a result, their effectiveness degrades substantially in practical IoT environments where noise and attacks interact. In this work, we propose a dual-factor adaptive and robust aggregation framework (DARA) to improve the stability of FL under such combined disturbances. DARA adjusts the differential privacy noise scale by jointly considering local update magnitudes and training-round dynamics, aiming to mitigate noise-induced bias under a fixed privacy budget. Meanwhile, a direction-aware weighted aggregation scheme assigns continuous trust weights based on cosine similarity between updates, thereby suppressing the influence of potentially anomalous or adversarial clients. We conduct extensive experiments on multiple benchmark datasets to evaluate DARA under differential privacy constraints and Byzantine attack scenarios. The results indicate that DARA achieves favorable robustness and convergence behavior compared with representative aggregation baselines, while maintaining competitive model accuracy. Full article
(This article belongs to the Special Issue Federated Learning: Challenges, Methods, and Future Directions)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-1
Back to TopTop