Adarsh Kumar, Arjun Balasubramanian, Shivaram Venkataraman, and Aditya Akella, University of Wisconsin, Madison
Over the last few years, Deep Neural Networks (DNNs) have become ubiquitous owing to their high accuracy on real-world tasks. However, this increase in accuracy comes at the cost of computationally expensive models leading to higher prediction latencies. Prior efforts to reduce this latency such as quantization, model distillation, and any-time prediction models typically trade-off accuracy for performance. In this work, we observe that caching intermediate layer outputs can help us avoid running all the layers of a DNN for a sizeable fraction of inference requests. We find that this can potentially reduce the number of effective layers by half for 91.58% of CIFAR-10 requests run on ResNet-18. We present Freeze Inference, a system that introduces approximate caching at each intermediate layer and we discuss techniques to reduce the cache size and improve the cache hit rate. Finally, we discuss some of the open research challenges in realizing such a design.
Open Access Media
USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.
author = {Adarsh Kumar and Arjun Balasubramanian and Shivaram Venkataraman and Aditya Akella},
title = {Accelerating Deep Learning Inference via Freezing},
booktitle = {11th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 19)},
year = {2019},
address = {Renton, WA},
url = {https://www.usenix.org/conference/hotcloud19/presentation/kumar},
publisher = {USENIX Association},
month = jul
}