mlsanityData to 14 Oct 2026

Argus: Federated Non-convex Bilevel Learning over 6G Space-Air-Ground Integrated Network

arXiv 2505.09106 ↗First posted 14 May 2025cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

The space-air-ground integrated network (SAGIN) has recently emerged as a core element in the 6G networks. However, traditional centralized and synchronous optimization algorithms are unsuitable for SAGIN due to infrastructureless and time-varying environments. This paper aims to develop a novel Asynchronous algorithm a.k.a. Argus for tackling non-convex and non-smooth decentralized federated bilevel learning over SAGIN. The proposed algorithm allows networked agents (e.g. autonomous aerial vehicles) to tackle bilevel learning problems in time-varying networks asynchronously, thereby averting stragglers from impeding the overall training speed. We provide a theoretical analysis of the iteration complexity, communication complexity, and computational complexity of Argus. Its effectiveness is further demonstrated through numerical experiments.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 42 of its 78 references that are in the map. First posted on arXiv 14 May 2025.

Builds on

42 of 78 references.

References · 42

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2021Convex optimizationcited by 2,515
  5. 2016Matching Networks for One Shot Learningcited by 2,255
  6. 2019Optimizing Millions of Hyperparameters by Implicit Differentiationcited by 304
  7. 2019Asynchronous Federated Optimizationcited by 267
  8. 2017Forward and Reverse Gradient-Based Hyperparameter Optimizationcited by 234
  9. 2020Bilevel Optimization: Convergence Analysis and Enhanced Designcited by 222
  10. 2017Asynchronous Decentralized Parallel Stochastic Gradient Descentcited by 159
  11. 2020On the Iteration Complexity of Hypergradient Computationcited by 155
  12. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 138
30 more
  1. 2022Decentralized Training of Foundation Models in Heterogeneous Environmentscited by 87
  2. 2021Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimizationcited by 76
  3. 2018Reviving and Improving Recurrent Back-Propagationcited by 69
  4. 2020A Unified Single-loop Alternating Gradient Projection Algorithm for Nonconvex-Concave and Convex-Nonconcave Minimax Problemscited by 57
  5. 2017Curriculum Dropoutcited by 50
  6. 2021A Unified and Refined Convergence Analysis for Non-Convex Decentralized Learningcited by 44
  7. 2018Robust Optimization over Multiple Domainscited by 34
  8. 2022Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networkscited by 32
  9. 2022Decentralized Bilevel Optimizationcited by 23
  10. 2022Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexitycited by 21
  11. 2021MEDIC: A Multi-Task Learning Dataset for Disaster Image Classificationcited by 20
  12. 2021EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature Fusioncited by 18
  13. 2013Five Disruptive Technology Directions for 5Gcited by 15
  14. 2020Straggler-aware Distributed Learning: Communication Computation Latency Trade-offcited by 15
  15. 2021Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthinesscited by 15
  16. 2023AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devicescited by 15
  17. 2022On the Convergence of Distributed Stochastic Bilevel Optimization Algorithms over a Networkcited by 14
  18. 2022Distributed Distributionally Robust Optimization with Non-Convex Objectivescited by 14
  19. 2021ADOM: Accelerated Decentralized Optimization Method for Time-Varying Networkscited by 13
  20. 2022Asynchronous Decentralized Learning over Unreliable Wireless Networkscited by 13
  21. 2022Asynchronous Distributed Bilevel Optimizationcited by 13
  22. 2023Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problemcited by 13
  23. 2021Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspectivecited by 12
  24. 2022Proximal Stochastic Recursive Momentum Methods for Nonconvex Composite Decentralized Optimizationcited by 10
  25. 2022INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networkscited by 8
  26. 2022DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimizationcited by 7
  27. 2023Provably Convergent Federated Trilevel Learningcited by 6
  28. 2022Olive Branch Learning: A Topology-Aware Federated Learning Framework for Space-Air-Ground Integrated Networkcited by 5
  29. 2022Differentiated Federated Reinforcement Learning Based Traffic Offloading on Space-Air-Ground Integrated Networkscited by 4
  30. 2024Robust Beamforming for Downlink Multi-Cell Systems: A Bilevel Optimization Perspectivecited by 2

Built on by

Cited by year (2026 to 14 Oct)

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

2 papers.

  1. 2025From Language to Logic: A Bi-Level Framework for Structured Reasoningcited by 0
  2. 2026AsynDBT: Asynchronous Distributed Bilevel Tuning for efficient In-Context Learning with Large Language Modelscited by 0