mlsanityData to 14 Oct 2026

C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning

arXiv 2509.19674 ↗First posted 24 Sep 2025cs.LG cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Federated continual learning (FCL) tackles scenarios of learning from continuously emerging task data across distributed clients, where the key challenge lies in addressing both temporal forgetting over time and spatial forgetting simultaneously. Recently, prompt-based FCL methods have shown advanced performance through task-wise prompt communication.In this study, we underscore that the existing prompt-based FCL methods are prone to class-wise knowledge coherence between prompts across clients. The class-wise knowledge coherence includes two aspects: (1) intra-class distribution gap across clients, which degrades the learned semantics across prompts, (2) inter-prompt class-wise relevance, which highlights cross-class knowledge confusion. During prompt communication, insufficient class-wise coherence exacerbates knowledge conflicts among new prompts and induces interference with old prompts, intensifying both spatial and temporal forgetting. To address these issues, we propose a novel Class-aware Client Knowledge Interaction (C2Prompt) method that explicitly enhances class-wise knowledge coherence during prompt communication. Specifically, a local class distribution compensation mechanism (LCDC) is introduced to reduce intra-class distribution disparities across clients, thereby reinforcing intra-class knowledge consistency. Additionally, a class-aware prompt aggregation scheme (CPA) is designed to alleviate inter-class knowledge confusion by selectively strengthening class-relevant knowledge aggregation. Extensive experiments on multiple FCL benchmarks demonstrate that C2Prompt achieves state-of-the-art performance. Our source code is available at https://github.com/zhoujiahuan1991/NeurIPS2025-C2Prompt

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 67 of its 92 references that are in the map. First posted on arXiv 24 Sep 2025.

Builds on

67 of 92 references.

References · 67

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2016Learning without Forgettingcited by 2,496
  4. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  5. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  6. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  7. 2021Learning to Prompt for Continual Learningcited by 944
  8. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  9. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  10. 2021Model-Contrastive Federated Learningcited by 766
  11. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
  12. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
38 more
  1. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 642
  2. 2021Merging Models with Fisher-Weighted Averagingcited by 621
  3. 2019Gradient based sample selection for online continual learningcited by 571
  4. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  5. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  6. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  7. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 450
  8. 2022Dataless Knowledge Fusion by Merging Weights of Language Modelscited by 387
  9. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
  10. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 379
  11. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  12. 2021Rainbow Memory: Continual Learning with a Memory of Diverse Samplescited by 273
  13. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  14. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  15. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 161
  16. 2022Federated Class-Incremental Learningcited by 127
  17. 2023Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimalitycited by 121
  18. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  19. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  20. 2022FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learningcited by 66
  21. 2023TARGET: Federated Class-Continual Learning via Exemplar-Free Distillationcited by 65
  22. 2023Better Generative Replay for Continual Federated Learningcited by 55
  23. 2024Global and Local Prompts Cooperation via Optimal Transport for Federated Learningcited by 46
  24. 2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
  25. 2023Learning Federated Visual Prompt in Null Space for MRI Reconstructioncited by 40
  26. 2024MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learningcited by 36
  27. 2023Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Datacited by 35
  28. 2024Towards Efficient Replay in Federated Incremental Learningcited by 33
  29. 2024DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learningcited by 32
  30. 2022FedSynth: Gradient Compression via Synthetic Data in Federated Learningcited by 31
  31. 2023Asynchronous Federated Continual Learningcited by 29
  32. 2024Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domainscited by 28
  33. 2024Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learningcited by 23
  34. 2024Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Methodcited by 22
  35. 2024Closed-form merging of parameter-efficient modules for Federated Continual Learningcited by 22
  36. 2024Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matchingcited by 21
  37. 2024FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extractioncited by 21
  38. 2021Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detectioncited by 20

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Reviving Stale Updates: Data-Free Knowledge Distillation for Asynchronous Federated Learningcited by 0
  2. 2026Accurate and Resource-Efficient Federated Continual Learningcited by 0