mlsanityData to 14 Oct 2026

Task-Agnostic Federation over Decentralized Data: Research Landscape and Visions

arXiv 2503.03140 ↗First posted 5 Mar 2025cs.DC cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Increasing legislation and regulations on private and proprietary information results in scattered data sources also known as the "data islands". Although Federated Learning-based paradigms can enable privacy-preserving collaboration over decentralized data, they have inherent deficiencies in fairness, costs and reproducibility because of being learning-centric, which greatly limits the way how participants cooperate with each other. In light of this, we investigate the possibilities to shift from resource-intensive learning to task-agnostic collaboration especially when the participants have no interest in a common goal. We term this new scenario as Task-Agnostic Federation (TAF), and investigate several branches of research that serve as the technical building blocks. These techniques directly or indirectly embrace data-centric approaches that can operate independently of any learning task. In this article, we first describe the system architecture and problem setting for TAF. Then, we present a three-way roadmap and categorize recent studies in three directions: collaborative data expansion, collaborative data refinement, and collective data harmonization in the federation. Further, we highlight several challenges and open questions that deserve more attention from the community. With our investigation, we intend to offer new insights about how autonomic parties with varied motivation can cooperate over decentralized data beyond learning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 57 of its 122 references that are in the map. First posted on arXiv 5 Mar 2025.

Builds on

57 of 122 references.

References · 57

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  6. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  7. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  8. 2017Neural Collaborative Filteringcited by 1,111
  9. 2019Towards Federated Learning at Scale: System Designcited by 832
  10. 2019Confident Learning: Estimating Uncertainty in Dataset Labelscited by 413
  11. 2020Fairness in Machine Learning: A Surveycited by 370
  12. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 256
38 more
  1. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 252
  2. 2021Fast Yet Effective Machine Unlearningcited by 217
  3. 2020Can AI help in screening Viral and COVID-19 pneumonia?cited by 200
  4. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  5. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 138
  6. 2024Evaluation of OpenAI o1: Opportunities and Challenges of AGIcited by 127
  7. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  8. 2019Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation Systemcited by 79
  9. 2021Federated Reconstruction: Partially Local Federated Learningcited by 79
  10. 2020Compression of Deep Learning Models for Text: A Surveycited by 64
  11. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  12. 2022OpenFE: Automated Feature Generation with Expert-level Performancecited by 52
  13. 2024Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearningcited by 49
  14. 2022MetaFed: Federated Learning among Federations with Cyclic Knowledge Distillation for Personalized Healthcarecited by 37
  15. 2023How Re-sampling Helps for Long-Tail Learning?cited by 36
  16. 2021Emerging Trends in Federated Learning: From Model Fusion to Federated X Learningcited by 35
  17. 2022Federated Learning of Generative Image Priors for MRI Reconstructioncited by 33
  18. 2023FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneitycited by 33
  19. 2021Federated Neural Collaborative Filteringcited by 30
  20. 2020Convergence of Federated Learning over a Noisy Downlinkcited by 29
  21. 2022Machine Learning Security against Data Poisoning: Are We There Yet?cited by 23
  22. 2024Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learningcited by 23
  23. 2020Federated Machine Learning for Intelligent IoT via Reconfigurable Intelligent Surfacecited by 21
  24. 2024C-FedRAG: A Confidential Federated Retrieval-Augmented Generation Systemcited by 19
  25. 2021Applications of Federated Learning in Smart Cities: Recent Advances, Taxonomy, and Open Challengescited by 17
  26. 2023FedMEKT: Distillation-based Embedding Knowledge Transfer for Multimodal Federated Learningcited by 17
  27. 2024Tackling Noisy Clients in Federated Learning with End-to-end Label Correctioncited by 12
  28. 2021Federated Feature Selection for Cyber-Physical Systems of Systemscited by 11
  29. 2022Knowledge-augmented Deep Learning and Its Applications: A Surveycited by 10
  30. 2023Temporal Robustness against Data Poisoningcited by 10
  31. 2024Weakly Supervised Anomaly Detection via Knowledge-Data Alignmentcited by 10
  32. 2025Federated Retrieval Augmented Generation for Multi-Product Question Answeringcited by 10
  33. 2023Federated Analytics: A surveycited by 9
  34. 2024Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approachcited by 9
  35. 2025Adversarial Mixup Unlearningcited by 7
  36. 2024Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer Networkscited by 6
  37. 2022Resisting Deep Learning Models Against Adversarial Attack Transferability via Feature Randomizationcited by 5
  38. 2024Toward Efficient Data-Free Unlearningcited by 4

50 most cited of 57 All 57 (JSON)

Built on by

Not cited yet.