Early-Exit meets Model-Distributed Inference at Edge Networks
This work addresses efficiency challenges for edge computing applications, though it is incremental by combining existing early-exit and model-distributed techniques.
The paper tackles the problem of high communication costs in model-distributed inference at edge networks by integrating early-exit mechanisms, resulting in MDI-Exit processing more data at fixed accuracy and achieving higher accuracy for fixed data rates in experiments on NVIDIA Nano edge devices.
Distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire deep neural network (DNN) model but processes only a subset of the data. However, feeding the data to workers results in high communication costs, especially when the data is large. An emerging paradigm is model-distributed inference (MDI), where each worker carries only a subset of DNN layers. In MDI, a source device that has data processes a few layers of DNN and sends the output to a neighboring device, i.e., offloads the rest of the layers. This process ends when all layers are processed in a distributed manner. In this paper, we investigate the design and development of MDI with early-exit, which advocates that there is no need to process all the layers of a model for some data to reach the desired accuracy, i.e., we can exit the model without processing all the layers if target accuracy is reached. We design a framework MDI-Exit that adaptively determines early-exit and offloading policies as well as data admission at the source. Experimental results on a real-life testbed of NVIDIA Nano edge devices show that MDI-Exit processes more data when accuracy is fixed and results in higher accuracy for the fixed data rate.