Joseph Doyle

Mehran Salmani, Saeid Ghafouri, Alireza Sanaee et al.

The use of machine learning (ML) inference for various applications is growing drastically. ML inference services engage with users directly, requiring fast and accurate responses. Moreover, these services face dynamic workloads of requests, imposing changes in their computing resources. Failing to right-size computing resources results in either latency service level objectives (SLOs) violations or wasted computing resources. Adapting to dynamic workloads considering all the pillars of accuracy, latency, and resource cost is challenging. In response to these challenges, we propose InfAdapter, which proactively selects a set of ML model variants with their resource allocations to meet latency SLO while maximizing an objective function composed of accuracy and cost. InfAdapter decreases SLO violation and costs up to 65% and 33%, respectively, compared to a popular industry autoscaler (Kubernetes Vertical Pod Autoscaler).

Saeid Ghafouri, Kamran Razavi, Mehran Salmani et al.

Efficiently optimizing multi-model inference pipelines for fast, accurate, and cost-effective inference is a crucial challenge in machine learning production systems, given their tight end-to-end latency requirements. To simplify the exploration of the vast and intricate trade-off space of latency, accuracy, and cost in inference pipelines, providers frequently opt to consider one of them. However, the challenge lies in reconciling latency, accuracy, and cost trade-offs. To address this challenge and propose a solution to efficiently manage model variants in inference pipelines, we present IPA, an online deep learning Inference Pipeline Adaptation system that efficiently leverages model variants for each deep learning task. Model variants are different versions of pre-trained models for the same deep learning task with variations in resource requirements, latency, and accuracy. IPA dynamically configures batch size, replication, and model variants to optimize accuracy, minimize costs, and meet user-defined latency Service Level Agreements (SLAs) using Integer Programming. It supports multi-objective settings for achieving different trade-offs between accuracy and cost objectives while remaining adaptable to varying workloads and dynamic traffic patterns. Navigating a wider variety of configurations allows \namex{} to achieve better trade-offs between cost and accuracy objectives compared to existing methods. Extensive experiments in a Kubernetes implementation with five real-world inference pipelines demonstrate that IPA improves end-to-end accuracy by up to 21% with a minimal cost increase. The code and data for replications are available at https://github.com/reconfigurable-ml-pipeline/ipa.

Wei Dai, Joseph Doyle, Xiaodan Liang et al.

Chest X-ray (CXR) is one of the most commonly prescribed medical imaging procedures, often with over 2-10x more scans than other imaging modalities such as MRI, CT scan, and PET scans. These voluminous CXR scans place significant workloads on radiologists and medical practitioners. Organ segmentation is a crucial step to obtain effective computer-aided detection on CXR. In this work, we propose Structure Correcting Adversarial Network (SCAN) to segment lung fields and the heart in CXR images. SCAN incorporates a critic network to impose on the convolutional segmentation network the structural regularities emerging from human physiology. During training, the critic network learns to discriminate between the ground truth organ annotations from the masks synthesized by the segmentation network. Through this adversarial process the critic network learns the higher order structures and guides the segmentation model to achieve realistic segmentation outcomes. Extensive experiments show that our method produces highly accurate and natural segmentation. Using only very limited training data available, our model reaches human-level performance without relying on any existing trained model or dataset. Our method also generalizes well to CXR images from a different patient population and disease profiles, surpassing the current state-of-the-art.

Francesco Renna, Joseph Doyle, Vasileios Giotsas et al.

Audio/visual recognition and retrieval applications have recently garnered significant attention within Internet-of-Things (IoT) oriented services, given that video cameras and audio processing chipsets are now ubiquitous even in low-end embedded systems. In the most typical scenario for such services, each device extracts audio/visual features and compacts them into feature descriptors, which comprise media queries. These queries are uploaded to a remote cloud computing service that performs content matching for classification or retrieval applications. Two of the most crucial aspects for such services are: (i) controlling the device energy consumption when using the service; (ii) reducing the billing cost incurred from the cloud infrastructure provider. In this paper we derive analytic conditions for the optimal coupling between the device energy consumption and the incurred cloud infrastructure billing. Our framework encapsulates: the energy consumption to produce and transmit audio/visual queries, the billing rates of the cloud infrastructure, the number of devices concurrently connected to the same cloud server, {the query volume constraint of each cluster of devices,} and the statistics of the query data production volume per device. Our analytic results are validated via a deployment with: (i) the device side comprising compact image descriptors (queries) computed on Beaglebone Linux embedded platforms and transmitted to Amazon Web Services (AWS) Simple Storage Service; (ii) the cloud side carrying out image similarity detection via AWS Elastic Compute Cloud (EC2) instances, with the AWS Auto Scaling being used to control the number of instances according to the demand.