Toward Knowledge as a Service Over Networks: A Deep Learning Model Communication Paradigm

• Published in: IEEE journal on selected areas in communications 2019-06, Vol.37 (6), p.1349-1363
• Main Authors: Chen, Ziqian, Duan, Ling-Yu, Wang, Shiqi, Lou, Yihang, Huang, Tiejun, Wu, Dapeng Oliver, Gao, Wen
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Communication; Computational modeling; Data management; Data models; Deep learning; deep learning model communication; Interoperability; knowledge centric network; Knowledge engineering; Knowledge management; neural network compression; Neural networks; Redundancy; Standardization; Task analysis
• ISSN: 0733-8716; 1558-0008
• DOI: 10.1109/JSAC.2019.2904360

The advent of artificial intelligence and Internet of Things has led to the seamless transition turning the big data into the big knowledge. The deep learning models, which assimilate knowledge from large-scale data, can be regarded as an alternative but promising modality of knowledge for artificial intelligence services. Yet, the compression, storage, and communication of the deep learning models towards better knowledge services, especially over networks, pose a set of challenging problems on both industrial and academic realms. This paper presents the deep learning model communication paradigm based on multiple model compression, which greatly exploits the redundancy among multiple deep learning models in different application scenarios. We analyze the potential and demonstrate the promise of the compression strategy for deep learning model communication through a set of experiments. Moreover, the interoperability in deep learning model communication, which is enabled based on the standardization of compact deep learning model representation, is also discussed and envisioned.