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

arXiv: https://arxiv.org/abs/2505.09106 · HTML: https://mlsanity.com/paper/2505.09106/

## 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 (most cited first, 30 of 42)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Optimizing Millions of Hyperparameters by Implicit Differentiation](https://mlsanity.com/paper/1911.02590/) (2019)
- [Asynchronous Federated Optimization](https://mlsanity.com/paper/1903.03934/) (2019)
- [Forward and Reverse Gradient-Based Hyperparameter Optimization](https://mlsanity.com/paper/1703.01785/) (2017)
- [Bilevel Optimization: Convergence Analysis and Enhanced Design](https://mlsanity.com/paper/2010.07962/) (2020)
- [Asynchronous Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1710.06952/) (2017)
- [On the Iteration Complexity of Hypergradient Computation](https://mlsanity.com/paper/2006.16218/) (2020)
- [Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges](https://mlsanity.com/paper/2211.08413/) (2022)
- [Decentralized Training of Foundation Models in Heterogeneous Environments](https://mlsanity.com/paper/2206.01288/) (2022)
- [Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization](https://mlsanity.com/paper/2112.12376/) (2021)
- [Reviving and Improving Recurrent Back-Propagation](https://mlsanity.com/paper/1803.06396/) (2018)
- [A Unified Single-loop Alternating Gradient Projection Algorithm for Nonconvex-Concave and Convex-Nonconcave Minimax Problems](https://mlsanity.com/paper/2006.02032/) (2020)
- [Curriculum Dropout](https://mlsanity.com/paper/1703.06229/) (2017)
- [A Unified and Refined Convergence Analysis for Non-Convex Decentralized Learning](https://mlsanity.com/paper/2110.09993/) (2021)
- [Robust Optimization over Multiple Domains](https://mlsanity.com/paper/1805.07588/) (2018)
- [Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks](https://mlsanity.com/paper/2206.10870/) (2022)
- [Decentralized Bilevel Optimization](https://mlsanity.com/paper/2206.05670/) (2022)
- [Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity](https://mlsanity.com/paper/2210.12839/) (2022)
- [MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification](https://mlsanity.com/paper/2108.12828/) (2021)
- [EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature Fusion](https://mlsanity.com/paper/2104.14006/) (2021)
- [Five Disruptive Technology Directions for 5G](https://mlsanity.com/paper/1312.0229/) (2013)
- [Straggler-aware Distributed Learning: Communication Computation Latency Trade-off](https://mlsanity.com/paper/2004.04948/) (2020)
- [Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthiness](https://mlsanity.com/paper/2108.03980/) (2021)
- [AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devices](https://mlsanity.com/paper/2312.10935/) (2023)
- [On the Convergence of Distributed Stochastic Bilevel Optimization Algorithms over a Network](https://mlsanity.com/paper/2206.15025/) (2022)
- [Distributed Distributionally Robust Optimization with Non-Convex Objectives](https://mlsanity.com/paper/2210.07588/) (2022)

## Built on by (most cited first, 2 of 2)

- [From Language to Logic: A Bi-Level Framework for Structured Reasoning](https://mlsanity.com/paper/2507.08501/) (2025)
- [AsynDBT: Asynchronous Distributed Bilevel Tuning for efficient In-Context Learning with Large Language Models](https://mlsanity.com/paper/2602.17694/) (2026)

## 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.