Integration of TinyML and LargeML: A Survey of 6G and Beyond

TL;DR

The paper surveys the integration of TinyML and LargeML for 6G and beyond, detailing the complementary strengths of edge-efficient on-device learning and powerful server-side analytics. It introduces bidirectional integration frameworks—transfer learning, federated transfer learning, split learning, and federated split learning—and discusses their variants (including TL, FTL, FML, FFMs, SL, and FSL) to enable resource-aware, privacy-preserving collaboration across edge and cloud. It reviews applications spanning data privacy, network security, management, intent-based networking, zero-touch networks, and BrainMeta, and identifies core challenges in standardization, resource orchestration, security, and real-time AI, offering concrete future research directions. The work emphasizes that a holistic TinyML–LargeML integration can deliver low-latency edge processing together with scalable, intelligent network optimization, advancing 6G toward ubiquitous connectivity, extreme performance, high intelligence, and strong privacy/sustainability.

Abstract

The transition from 5G networks to 6G highlights a significant demand for machine learning (ML). Deep learning models, in particular, have seen wide application in mobile networking and communications to support advanced services in emerging wireless environments, such as smart healthcare, smart grids, autonomous vehicles, aerial platforms, digital twins, and the metaverse. The rapid expansion of Internet-of-Things (IoT) devices, many with limited computational capabilities, has accelerated the development of tiny machine learning (TinyML) and resource-efficient ML approaches for cost-effective services. However, the deployment of large-scale machine learning (LargeML) solutions require major computing resources and complex management strategies to support extensive IoT services and ML-generated content applications. Consequently, the integration of TinyML and LargeML is projected as a promising approach for future seamless connectivity and efficient resource management. Although the integration of TinyML and LargeML shows abundant potential, several challenges persist, including performance optimization, practical deployment strategies, effective resource management, and security considerations. In this survey, we review and analyze the latest research aimed at enabling the integration of TinyML and LargeML models for the realization of smart services and applications in future 6G networks and beyond. The paper concludes by outlining critical challenges and identifying future research directions for the holistic integration of TinyML and LargeML in next-generation wireless networks.

Figures (14)

• Figure 1: Transition from 5G to 6G and beyond (B6G): From target throughputs to use cases, core technologies, and emerging applications.
• Figure 2: Overview of TinyML and LargeML: life cycle, design, operation, and performance evaluation.
• Figure 3: Envisaged 6G capabilities and corresponding pivotal general requirements.
• Figure 4: TinyML--LargeML system with TL.
• Figure 5: TinyML--LargeML system with FTL.