Low-Latency Speculative Inference on Distributed Multi-Modal Data Streams

Abstract

While multi-modal deep learning is useful in distributed sensing tasks like human tracking, activity recognition, and audio and video analysis, deploying state-of-the-art multi-modal models in a wirelessly networked sensor system poses unique challenges. The data sizes for different modalities can be highly asymmetric (e.g., video vs. audio), and these differences can lead to significant delays between streams in the presence of wireless dynamics. Therefore, a slow stream can significantly slow down a multimodal inference system in the cloud, leading to either increased latency (when blocked by the slow stream) or degradation in inference accuracy (if inference proceeds without waiting).