mlsanityData to 14 Oct 2026

FedLTLib: A Comprehensive Benchmark for Federated Long-Tail Learning

arXiv 2609.15625 ↗First posted 14 Sep 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Driven by the escalating demand for privacy-preserving computing, Federated Learning (FL) has witnessed remarkable progress, becoming a cornerstone technology for bridging distributed data silos in mobile edge networks. However, in real-world mobile computing environments, data is generated by heterogeneous mobile devices with varying user behaviors, leading to a significant Long-Tail Distribution. Unlike idealized balanced datasets, data in the wild manifests an acute imbalance where a minority of head classes dominate the sample space while a vast number of tail classes, often representing rare but critical edge-case events, are extremely scarce. This data heterogeneity, which we formally characterize as "Double Heterogeneity", referring to the superposition of global class imbalance and local statistical skew, precipitates severe performance deterioration on tail classes, thereby spurring the vital research direction of Federated Long-Tail Learning (FL-LT). To standardize evaluation and accelerate research in this field, we introduce FedLTLib, a comprehensive benchmark tailored for FL-LT. Addressing the critical issues of inconsistent experimental configurations and unfair comparisons in prior work, FedLTLib establishes a standardized evaluation framework. The platform not only incorporates diverse benchmark datasets reflecting mobile data characteristics but also implements 13 state-of-the-art FL algorithms (4 traditional FL algorithms and 9 FL-LT algorithms). By leveraging FedLTLib, researchers can perform fair and reproducible evaluations of algorithm robustness and generalization capabilities under a unified experimental protocol, ultimately advancing the deployment of robust intelligence in mobile computing ecosystems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 40 references that are in the map. First posted on arXiv 14 Sep 2026.

Builds on

33 of 40 references.

References · 33

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2022Visual Prompt Tuningcited by 1,681
  5. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  7. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  8. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  9. 2018LEAF: A Benchmark for Federated Settingscited by 792
  10. 2021Model-Contrastive Federated Learningcited by 766
  11. 2020Long-tail learning via logit adjustmentcited by 618
  12. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
21 more
  1. 2021Deep Long-Tailed Learning: A Surveycited by 417
  2. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  3. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  4. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 300
  5. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  6. 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 136
  7. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  8. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 109
  9. 2022Decentralized Training of Foundation Models in Heterogeneous Environmentscited by 87
  10. 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 81
  11. 2023Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimizationcited by 65
  12. 2022Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Featurescited by 63
  13. 2023No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifiercited by 55
  14. 2025Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Modelscited by 46
  15. 2022pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learningcited by 44
  16. 2022FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillationcited by 19
  17. 2023Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancercited by 17
  18. 2025A Survey on Parameter-Efficient Fine-Tuning for Foundation Models in Federated Learningcited by 17
  19. 2024Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Datacited by 14
  20. 2024FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Datacited by 10
  21. 2025You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Datacited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Federated Learning: A Survey on Privacy-Preserving Collaborative Intelligence
  2. 2026FedGUI: Benchmarking Federated GUI Agents across Heterogeneous Platforms, Devices, and Operating Systems
  3. 2023Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data Heterogeneity
  4. 2025Towards a Larger Model via One-Shot Federated Learning on Heterogeneous Client Models
  5. 2026Quantization in Federated Learning: Methods, Challenges and Future Directions
  6. 2025Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy
  7. 2025CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model
  8. 2026FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices