mlsanityData to 14 Oct 2026

Trust-free Personalized Decentralized Learning

arXiv 2410.11378 ↗First posted 15 Oct 2024cs.LG cs.AI cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Personalized collaborative learning in federated settings faces a critical trade-off between customization and participant trust. Existing approaches typically rely on centralized coordinators or trusted peer groups, limiting their applicability in open, trust-averse environments. While recent decentralized methods explore anonymous knowledge sharing, they often lack global scalability and robust mechanisms against malicious peers. To bridge this gap, we propose TPFed, a textitTrust-free Personalized Decentralized Federated Learning framework. TPFed replaces central aggregators with a blockchain-based bulletin board, enabling participants to dynamically select global communication partners based on Locality-Sensitive Hashing (LSH) and peer ranking. Crucially, we introduce an ``all-in-one'' knowledge distillation protocol that simultaneously handles knowledge transfer, model quality evaluation, and similarity verification via a public reference dataset. This design ensures secure, globally personalized collaboration without exposing local models or data. Extensive experiments demonstrate that TPFed significantly outperforms traditional federated baselines in both learning accuracy and system robustness against adversarial attacks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 44 references that are in the map. First posted on arXiv 15 Oct 2024.

Builds on

15 of 44 references.

References · 15

  1. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  2. 2019Towards Federated Learning at Scale: System Designcited by 832
  3. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  4. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
  5. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
  6. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 138
  7. 2022Filter-enhanced MLP is All You Need for Sequential Recommendationcited by 96
  8. 2021Decentralized Federated Learning through Proxy Model Sharingcited by 57
  9. 2021Self-Supervised Graph Co-Training for Session-based Recommendationcited by 43
  10. 2022Architecture Agnostic Federated Learning for Neural Networkscited by 30
  11. 2023Personalized Decentralized Federated Learning with Knowledge Distillationcited by 21
  12. 2023Offline Learning in Markov Games with General Function Approximationcited by 18
3 more
  1. 2021Semi-Decentralized Federated Edge Learning with Data and Device Heterogeneitycited by 12
  2. 2024Proximity-based Self-Federated Learningcited by 5
  3. 2022Heterogeneous Collaborative Learning for Personalized Healthcare Analytics via Messenger Distillationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher
  2. 2025Scaling Decentralized Learning with FLock
  3. 2024Blockchain-enabled Trustworthy Federated Unlearning
  4. 2025A Novel Algorithm for Personalized Federated Learning: Knowledge Distillation with Weighted Combination Loss
  5. 2026BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning
  6. 2025Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attacks
  7. 2022Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillation
  8. 2025BDPFL: Backdoor Defense for Personalized Federated Learning via Explainable Distillation