mlsanityData to 14 Oct 2026

MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning in LEO Satellites

arXiv 2604.02356 ↗First posted 14 Mar 2026cs.NI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Low-Earth-orbit (LEO) satellite constellations are increasingly performing on-board computing. However, the continuous emergence of new classes under strict memory and communication constraints poses major challenges for collaborative training. Federated class-incremental learning (FCIL) enables distributed incremental learning without sharing raw data, but faces three LEO-specific challenges: non-independent and identically distributed data heterogeneity caused by orbital dynamics, amplified catastrophic forgetting during aggregation, and the need to balance stability and plasticity under limited resources. To tackle these challenges, we propose MLFCIL, a multi-level forgetting mitigation framework that decomposes catastrophic forgetting into three sources and addresses them at different levels: class-reweighted loss to reduce local bias, knowledge distillation with feature replay and prototype-guided drift compensation to preserve cross-task knowledge, and class-aware aggregation to mitigate forgetting during federation. In addition, we design a dual-granularity coordination strategy that combines round-level adaptive loss balancing with step-level gradient projection to further enhance the stability-plasticity trade-off. Experiments on the NWPU-RESISC45 dataset show that MLFCIL significantly outperforms baselines in both accuracy and forgetting mitigation, while introducing minimal resource overhead.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 39 references that are in the map. First posted on arXiv 14 Mar 2026.

Builds on

17 of 39 references.

References · 17

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  3. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 797
  4. 2023Class-Incremental Learning: A Surveycited by 209
  5. 2023TARGET: Federated Class-Continual Learning via Exemplar-Free Distillationcited by 65
  6. 2023No One Left Behind: Real-World Federated Class-Incremental Learningcited by 53
  7. 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
  8. 2025Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Modelscited by 46
  9. 2023FedSN: A Federated Learning Framework over Heterogeneous LEO Satellite Networkscited by 38
  10. 2024SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Frameworkcited by 21
  11. 2024PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learningcited by 19
  12. 2023Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learningcited by 18
5 more
  1. 2024ESFL: Efficient Split Federated Learning over Resource-Constrained Heterogeneous Wireless Devicescited by 16
  2. 2024Advances in Robust Federated Learning: A Survey with Heterogeneity Considerationscited by 12
  3. 2023Optimizing Federated Learning in LEO Satellite Constellations via Intra-Plane Model Propagation and Sink Satellite Schedulingcited by 10
  4. 2025Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgettingcited by 9
  5. 2024PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learningcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Resource-Aware Federated Mixture-of-Experts with Adaptive Pruning for Onboard Learning in LEO Satellite Constellations
  2. 2026Catastrophic Forgetting Resilient One-Shot Incremental Federated Learning
  3. 2023One-Shot Federated Learning for LEO Constellations that Reduces Convergence Time from Days to 90 Minutes
  4. 2025A Semi-Supervised Federated Learning Framework with Hierarchical Clustering Aggregation for Heterogeneous Satellite Networks
  5. 2026From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity
  6. 2023Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation
  7. 2025OptiVote: Non-Coherent FSO Over-the-Air Majority Vote for Communication-Efficient Distributed Federated Learning in Space Data Centers
  8. 2026Spatiotemporal Continual Federated Learning for Agentic Multi-UAV Edge Networks: Mitigating Catastrophic Forgetting