Split and Aggregation Learning for Foundation Models Over Mobile Embodied AI Network (MEAN): A Comprehensive Survey

TL;DR

This survey reviews split and aggregation learning methods for foundation models in 6G wireless systems, emphasizing their architectures, applications, and benefits for distributed AI in future networks.

Contribution

It provides a comprehensive analysis of split and aggregation learning paradigms, their integration with 6G technologies, and their roles in enabling privacy-preserving, scalable distributed AI.

Findings

SL and AL improve communication efficiency and data privacy in distributed AI.

Different configurations of SL and AL suit various data and privacy scenarios.

SL and AL are key to enabling scalable, privacy-preserving foundation models in 6G networks.

Abstract

The rapid advancements in foundation models and sixth-generation (6G) wireless communication systems necessitate the development of efficient, scalable, and privacy-preserving machine learning approaches. For foundation models in 6G, split learning (SL) and aggregation learning (AL) have emerged as promising paradigms that address key challenges in distributed artificial intelligence (AI), such as communication efficiency, resource allocation, and data privacy. SL enables multiple entities to collaboratively train deep learning models by partitioning neural networks, while AL focuses on aggregating intermediate results or model updates from multiple participants, improving robustness, optimizing resource utilization, and mitigating data leakage risks. Specifically, SL is ideal for scenarios requiring strict data isolation (e.g., vertical collaborations), whereas AL suits homogeneous horizontal data settings; they can be combined to balance privacy and communication efficiency. This survey provides a comprehensive analysis of SL and AL in 6G communication systems, exploring their architectures, technical methodologies, and integration with AI-native 6G communication technologies. We examine different SL configurations, aggregation techniques, and their roles in optimizing distributed foundation models. Furthermore, we discuss their applications in emerging wireless networks, including semantic communication, reconfigurable intelligent surfaces (RIS), space-air-ground integrated networks (SAGINs), and quantum communication. By analyzing the impact of SL and AL, this survey provides insights into their role in shaping distributed AI-driven communication systems in the 6G era, focusing on efficiency, privacy preservation, and scalability.