With the introduction of 5G/6G, advanced networking / computing technologies, and Internet of Things / industrial Internet of Things, communication networks are turning into a complex system. Whilst it offers services to end users and vertical industries with more satisfying quality of experience, it raises the bar for network management. Machine learning including deep learning and deep reinforcement learning, has been widely adopted to facilitate network management for complex communication networks and future Internet. They provide useful tools for automating data collection, network analytics, and decision making, leading to autonomous networks / zero touch networks. Such machine learning powered tools perform well under many network conditions but may behave unexpectedly in certain network settings. Due to the “black-box” nature and the lack of explainability, machine learning powered network management tools cannot be fully interpreted and can therefore not be regulated properly under certain network settings.

Explainable AI (XAI) has been studied for a couple of years. Its application in the network domain has been deemed to be of paramount importance toward the success of wide adoption and deployment of machine learning powered network management tools. The research in this area has received significant attention in recent years but there are still many challenging and open issues to be addressed. This workshop will address the important problems and challenges of explainable AI for network management and future Internet. The workshop aims to bring together computer scientists and engineers in different disciplines to share and exchange their experience and ideas and discuss state-of-the-art and in-progress research on all aspects of explainable AI for network management and future Internet.

Topics of interest include but are not limited to: