Interpreting Deep Learning-Based Networking Systems
This addresses the interpretability issue for network operators deploying deep learning systems, though it is incremental as it builds on existing methods for known bottlenecks.
The paper tackles the problem of deep learning-based networking systems being uninterpretable black boxes, which hinders deployment, by proposing Metis, a framework that provides human-readable interpretations while preserving performance with nearly no degradation.
While many deep learning (DL)-based networking systems have demonstrated superior performance, the underlying Deep Neural Networks (DNNs) remain blackboxes and stay uninterpretable for network operators. The lack of interpretability makes DL-based networking systems prohibitive to deploy in practice. In this paper, we propose Metis, a framework that provides interpretability for two general categories of networking problems spanning local and global control. Accordingly, Metis introduces two different interpretation methods based on decision tree and hypergraph, where it converts DNN policies to interpretable rule-based controllers and highlight critical components based on analysis over hypergraph. We evaluate Metis over several state-of-the-art DL-based networking systems and show that Metis provides human-readable interpretations while preserving nearly no degradation in performance. We further present four concrete use cases of Metis, showcasing how Metis helps network operators to design, debug, deploy, and ad-hoc adjust DL-based networking systems.