INSIGHT: A Survey of In-Network Systems for Intelligent, High-Efficiency AI and Topology Optimization

TL;DR

This survey explores how in-network computation can enhance AI workloads by leveraging programmable network devices, discussing architectures, methodologies, applications, and future research directions.

Contribution

It provides a comprehensive overview of in-network AI systems, analyzing architectures, methodologies, and applications, and proposing future research directions.

Findings

In-network computation reduces AI workload latency and improves throughput.

Frameworks like Planter and Quark facilitate development of in-network AI solutions.

In-network aggregation and federated learning enhance privacy and scalability.

Abstract

In-network computation represents a transformative approach to addressing the escalating demands of Artificial Intelligence (AI) workloads on network infrastructure. By leveraging the processing capabilities of network devices such as switches, routers, and Network Interface Cards (NICs), this paradigm enables AI computations to be performed directly within the network fabric, significantly reducing latency, enhancing throughput, and optimizing resource utilization. This paper provides a comprehensive analysis of optimizing in-network computation for AI, exploring the evolution of programmable network architectures, such as Software-Defined Networking (SDN) and Programmable Data Planes (PDPs), and their convergence with AI. It examines methodologies for mapping AI models onto resource-constrained network devices, addressing challenges like limited memory and computational capabilities through efficient algorithm design and model compression techniques. The paper also highlights advancements in distributed learning, particularly in-network aggregation, and the potential of federated learning to enhance privacy and scalability. Frameworks like Planter and Quark are discussed for simplifying development, alongside key applications such as intelligent network monitoring, intrusion detection, traffic management, and Edge AI. Future research directions, including runtime programmability, standardized benchmarks, and new applications paradigms, are proposed to advance this rapidly evolving field. This survey underscores the potential of in-network AI to create intelligent, efficient, and responsive networks capable of meeting the demands of next-generation AI applications.