Learning and Communications Co-Design for Remote Inference Systems: Feature Length Selection and Transmission Scheduling

In this paper, we consider a remote inference system, where a neural network is used to infer a time-varying target (e.g., robot movement), based on features (e.g., video clips) that are progressively received from a sensing node (e.g., a camera). Each feature is a temporal sequence of sensory data. The learning performance of the system is determined by (i) the timeliness and (ii) the temporal sequence length of the features, where we use Age of Information (AoI) as a metric for timeliness. While a longer feature can typically provide better learning performance, it often requires more channel resources for sending the feature. To minimize the time-averaged inference error, we study a learning and communication co-design problem that jointly optimizes feature length selection and transmission scheduling. When there is a single sensor-predictor pair and a single channel, we develop low-complexity optimal co-designs for both the cases of time-invariant and time-variant feature length. When there are multiple sensor-predictor pairs and multiple channels, the co-design problem becomes a restless multi-arm multi-action bandit problem that is PSPACE-hard. For this setting, we design a low-complexity algorithm to solve the problem. Trace-driven evaluations suggest that the proposed co-designs can significantly reduce the time-averaged inference error of remote inference systems.