Model-as-a-Service (MaaS): A Survey

TL;DR

This survey explores the emerging Model-as-a-Service paradigm in generative AI, highlighting its development, key technologies, applications, challenges, and future directions to democratize access to powerful foundation models.

Contribution

It provides a comprehensive overview of MaaS, including its history, technological foundations, recent applications, and future challenges, serving as a foundational reference for future research.

Findings

MaaS enables scalable deployment of foundation models.

Recent applications demonstrate MaaS's broad industry impact.

Challenges include infrastructure, ethics, and model governance.

Abstract

Due to the increased number of parameters and data in the pre-trained model exceeding a certain level, a foundation model (e.g., a large language model) can significantly improve downstream task performance and emerge with some novel special abilities (e.g., deep learning, complex reasoning, and human alignment) that were not present before. Foundation models are a form of generative artificial intelligence (GenAI), and Model-as-a-Service (MaaS) has emerged as a groundbreaking paradigm that revolutionizes the deployment and utilization of GenAI models. MaaS represents a paradigm shift in how we use AI technologies and provides a scalable and accessible solution for developers and users to leverage pre-trained AI models without the need for extensive infrastructure or expertise in model training. In this paper, the introduction aims to provide a comprehensive overview of MaaS, its significance, and its implications for various industries. We provide a brief review of the development history of "X-as-a-Service" based on cloud computing and present the key technologies involved in MaaS. The development of GenAI models will become more democratized and flourish. We also review recent application studies of MaaS. Finally, we highlight several challenges and future issues in this promising area. MaaS is a new deployment and service paradigm for different AI-based models. We hope this review will inspire future research in the field of MaaS.