mlsanityData to 7 Oct 2026

Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning

arXiv 2405.15632 ↗First posted 24 May 2024cs.LG cs.DCcited by 3

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL), a privacy-aware approach in distributed deep learning environments, enables many clients to collaboratively train a model without sharing sensitive data, thereby reducing privacy risks. However, enabling human trust and control over FL systems requires understanding the evolving behaviour of clients, whether beneficial or detrimental for the training, which still represents a key challenge in the current literature. To address this challenge, we introduce Federated Behavioural Planes (FBPs), a novel method to analyse, visualise, and explain the dynamics of FL systems, showing how clients behave under two different lenses: predictive performance (error behavioural space) and decision-making processes (counterfactual behavioural space). Our experiments demonstrate that FBPs provide informative trajectories describing the evolving states of clients and their contributions to the global model, thereby enabling the identification of clusters of clients with similar behaviours. Leveraging the patterns identified by FBPs, we propose a robust aggregation technique named Federated Behavioural Shields to detect malicious or noisy client models, thereby enhancing security and surpassing the efficacy of existing state-of-the-art FL defense mechanisms. Our code is publicly available on GitHub.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 39 of its 70 references that are in the map. First posted on arXiv 24 May 2024.

Builds on

39 of 70 references.

References · 39

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  6. 2018How To Backdoor Federated Learningcited by 745
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  8. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  9. 2020An Efficient Framework for Clustered Federated Learningcited by 505
  10. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  11. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
  12. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
27 more
  1. 2020Learning under Concept Drift: A Reviewcited by 470
  2. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 449
  3. 2015Illuminating search spaces by mapping elitescited by 406
  4. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  5. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  6. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  7. 2019Robust Aggregation for Federated Learningcited by 314
  8. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  9. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 285
  10. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  11. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 222
  12. 2020Threats to Federated Learning: A Surveycited by 171
  13. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 163
  14. 2018SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systemscited by 148
  15. 2019Learning Model-Agnostic Counterfactual Explanations for Tabular Datacited by 146
  16. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 136
  17. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  18. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 125
  19. 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 112
  20. 2019Free-riders in Federated Learning: Attacks and Defensescited by 48
  21. 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
  22. 2021Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learningcited by 46
  23. 2019Abnormal Client Behavior Detection in Federated Learningcited by 39
  24. 2022FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distributioncited by 22
  25. 2022VCNet: A self-explaining model for realistic counterfactual generationcited by 20
  26. 2023Bias Propagation in Federated Learningcited by 12
  27. 2022HetVis: A Visual Analysis Approach for Identifying Data Heterogeneity in Horizontal Federated Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Federated Concept-Based Models: Interpretable models with distributed supervisioncited by 0
  2. 2026Federated Learning with Energy-Based Structured Probabilistic Inferencecited by 0
  3. 2026Semantic Space Search Trajectory Networkscited by 0