mlsanityData to 7 Oct 2026

LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networks

arXiv 2501.01293 ↗First posted 2 Jan 2025cs.LG cs.AI cs.DCcited by 22

Not on the map. Why?

Abstract (arXiv)

Recently, the increasing deployment of LEO satellite systems has enabled various space analytics (e.g., crop and climate monitoring), which heavily relies on the advancements in deep learning (DL). However, the intermittent connectivity between LEO satellites and ground station (GS) significantly hinders the timely transmission of raw data to GS for centralized learning, while the scaled-up DL models hamper distributed learning on resource-constrained LEO satellites. Though split learning (SL) can be a potential solution to these problems by partitioning a model and offloading primary training workload to GS, the labor-intensive labeling process remains an obstacle, with intermittent connectivity and data heterogeneity being other challenges. In this paper, we propose LEO-Split, a semi-supervised (SS) SL design tailored for satellite networks to combat these challenges. Leveraging SS learning to handle (labeled) data scarcity, we construct an auxiliary model to tackle the training failure of the satellite-GS non-contact time. Moreover, we propose a pseudo-labeling algorithm to rectify data imbalances across satellites. Lastly, an adaptive activation interpolation scheme is devised to prevent the overfitting of server-side sub-model training at GS. Extensive experiments with real-world LEO satellite traces (e.g., Starlink) demonstrate that our LEO-Split framework achieves superior performance compared to state-ofthe-art benchmarks.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 25 of its 68 references that are in the map. First posted on arXiv 2 Jan 2025.

Builds on

25 of 68 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  6. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  7. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  8. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  9. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  10. 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
  11. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  12. 2022Federated Learning with Partial Model Personalizationcited by 114
13 more
  1. 2023Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networkscited by 95
  2. 2023Split Learning in 6G Edge Networkscited by 68
  3. 2024AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networkscited by 64
  4. 2023Revisiting Weighted Aggregation in Federated Learning with Neural Networkscited by 57
  5. 2020Mitigating Bias in Federated Learningcited by 56
  6. 2024Hierarchical Split Federated Learning: Convergence Analysis and System Optimizationcited by 38
  7. 2022FedSpace: An Efficient Federated Learning Framework at Satellites and Ground Stationscited by 28
  8. 2022FedHAP: Fast Federated Learning for LEO Constellations Using Collaborative HAPscited by 21
  9. 2022SplitGP: Achieving Both Generalization and Personalization in Federated Learningcited by 20
  10. 2024SATSense: Multi-Satellite Collaborative Framework for Spectrum Sensingcited by 14
  11. 2024Communication-Efficient Federated Learning for LEO Satellite Networks Integrated with HAPs Using Hybrid NOMA-OFDMcited by 6
  12. 2022Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computingcited by 5
  13. 2024S4: Self-Supervised Sensing Across the Spectrumcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 15; 2026: 7.

22 papers.

Sort:

By area:

  1. 2025HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 30
  2. 2025HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systemscited by 15
  3. 2026Multimodal Multi-Agent Empowered Legal Judgment Predictioncited by 14
  4. 2025LLM-Driven Stationarity-Aware Expert Demonstrations for Multi-Agent Reinforcement Learning in Mobile Systemscited by 8
  5. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learningcited by 7
  6. 2025Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attackscited by 7
  7. 2025SL-ACC: A Communication-Efficient Split Learning Framework with Adaptive Channel-wise Compressioncited by 6
  8. 2025LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learningcited by 6
  9. 2025Rethinking Membership Inference Attacks Against Transfer Learningcited by 5
  10. 2025Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generationcited by 3
  11. 2025Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edgecited by 2
  12. 2025A Satellite-Ground Synergistic Large Vision-Language Model System for Earth Observationcited by 2
10 more
  1. 2025Sample Efficient Experience Replay in Non-stationary Environmentscited by 2
  2. 2025Secure Resource Allocation via Constrained Deep Reinforcement Learningcited by 1
  3. 2025SFL-LEO: Asynchronous Split-Federated Learning Design for LEO Satellite-Ground Network Frameworkcited by 1
  4. 2026ASFL: An Adaptive Model Splitting and Resource Allocation Framework for Split Federated Learningcited by 1
  5. 2026Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classificationcited by 1
  6. 2025DP-TRAE: A Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protectioncited by 0
  7. 2026SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacycited by 0
  8. 2026GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systemscited by 0
  9. 2026Conflict-Aware Federated Fine-Tuning of Large Language Models with Mixture-of-Expertscited by 0
  10. 2026Bridging the Gap between Labeled and Unlabeled Data via Unified Flow with Feature Memory Bankcited by 0