skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Neural Network Partitioning for Fast Distributed Inference
The rising availability of heterogeneous networked devices highlights new opportunities for distributed artificial intelligence. This work proposes an Integer Linear Programming (ILP) optimization scheme to assign layers of a neural network in a distributed setting with heterogeneous devices representing edge, hub, and cloud in order to minimize the overall inference latency. The ILP formulation captures the tradeoff between avoiding communication cost when executing consecutive layers on the same device versus the latency benefit due to weight preloading when an idle device is waiting to receive the results of an earlier layer across the network. In our experiments we show the layer assignment and inference latency of a neural network can significantly vary depending on the types of devices in the network and their communications bandwidths.  more » « less
Award ID(s):
2006394
PAR ID:
10520403
Author(s) / Creator(s):
;
Publisher / Repository:
IEEE
Date Published:
ISBN:
979-8-3503-3475-3
Page Range / eLocation ID:
1 to 7
Format(s):
Medium: X
Location:
San Francisco, CA, USA
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Advances in Neural Information Processing Systems)
    Hybrid Privacy-Preserving Neural Network (HPPNN) implementing linear layers by Homomorphic Encryption (HE) and nonlinear layers by Garbled Circuit (GC) is one of the most promising secure solutions to emerging Machine Learning as a Service (MLaaS). Unfortunately, a HPPNN suffers from long inference latency, e.g., ∼100 seconds per image, which makes MLaaS unsatisfactory. Because HE-based linear layers of a HPPNN cost 93% inference latency, it is critical to select a set of HE parameters to minimize computational overhead of linear layers. Prior HPPNNs over-pessimistically select huge HE parameters to maintain large noise budgets, since they use the same set of HE parameters for an entire network and ignore the error tolerance capability of a network. In this paper, for fast and accurate secure neural network inference, we propose an automated layer-wise parameter selector, AutoPrivacy, that leverages deep reinforcement learning to automatically determine a set of HE parameters for each linear layer in a HPPNN. The learning-based HE parameter selection policy outperforms conventional rule-based HE parameter selection policy. Compared to prior HPPNNs, AutoPrivacy-optimized HPPNNs reduce inference latency by 53%∼70% with negligible loss of accuracy. 
    more » « less
  2. ; ; (, ICPP '23: Proceedings of the 52nd International Conference on Parallel Processing)
    Deep neural network (DNN) inference poses unique challenges in serving computational requests due to high request intensity, concurrent multi-user scenarios, and diverse heterogeneous service types. Simultaneously, mobile and edge devices provide users with enhanced computational capabilities, enabling them to utilize local resources for deep inference processing. Moreover, dynamic inference techniques allow content-based computational cost selection per request. This paper presents Dystri, an innovative framework devised to facilitate dynamic inference on distributed edge infrastructure, thereby accommodating multiple heterogeneous users. Dystri offers a broad applicability in practical environments, encompassing heterogeneous device types, DNN-based applications, and dynamic inference techniques, surpassing the state-of-the-art (SOTA) approaches. With distributed controllers and a global coordinator, Dystri allows per-request, per-user adjustments of quality-of-service, ensuring instantaneous, flexible, and discrete control. The decoupled workflows in Dystri naturally support user heterogeneity and scalability, addressing crucial aspects overlooked by existing SOTA works. Our evaluation involves three multi-user, heterogeneous DNN inference service platforms deployed on distributed edge infrastructure, encompassing seven DNN applications. Results show Dystri achieves near-zero deadline misses and excels in adapting to varying user numbers and request intensities. Dystri outperforms baselines with accuracy improvement up to 95 ×. 
    more » « less
  3. ; ; ; ; (, Proceedings of the ACM on Measurement and Analysis of Computing Systems)
    Convolutional neural networks (CNNs) are used in numerous real-world applications such as vision-based autonomous driving and video content analysis. To run CNN inference on various target devices, hardware-aware neural architecture search (NAS) is crucial. A key requirement of efficient hardware-aware NAS is the fast evaluation of inference latencies in order to rank different architectures. While building a latency predictor for each target device has been commonly used in state of the art, this is a very time-consuming process, lacking scalability in the presence of extremely diverse devices. In this work, we address the scalability challenge by exploiting latency monotonicity --- the architecture latency rankings on different devices are often correlated. When strong latency monotonicity exists, we can re-use architectures searched for one proxy device on new target devices, without losing optimality. In the absence of strong latency monotonicity, we propose an efficient proxy adaptation technique to significantly boost the latency monotonicity. Finally, we validate our approach and conduct experiments with devices of different platforms on multiple mainstream search spaces, including MobileNet-V2, MobileNet-V3, NAS-Bench-201, ProxylessNAS and FBNet. Our results highlight that, by using just one proxy device, we can find almost the same Pareto-optimal architectures as the existing per-device NAS, while avoiding the prohibitive cost of building a latency predictor for each device. 
    more » « less
  4. ; ; ; (, ACM Transactions on Embedded Computing Systems)
    Domain specific neural network accelerators have garnered attention because of their improved energy efficiency and inference performance compared to CPUs and GPUs. Such accelerators are thus well suited for resource-constrained embedded systems. However, mapping sophisticated neural network models on these accelerators still entails significant energy and memory consumption, along with high inference time overhead. Binarized neural networks (BNNs), which utilize single-bit weights, represent an efficient way to implement and deploy neural network models on accelerators. In this paper, we present a novel optical-domain BNN accelerator, named ROBIN , which intelligently integrates heterogeneous microring resonator optical devices with complementary capabilities to efficiently implement the key functionalities in BNNs. We perform detailed fabrication-process variation analyses at the optical device level, explore efficient corrective tuning for these devices, and integrate circuit-level optimization to counter thermal variations. As a result, our proposed ROBIN architecture possesses the desirable traits of being robust, energy-efficient, low latency, and high throughput, when executing BNN models. Our analysis shows that ROBIN can outperform the best-known optical BNN accelerators and many electronic accelerators. Specifically, our energy-efficient ROBIN design exhibits energy-per-bit values that are ∼4 × lower than electronic BNN accelerators and ∼933 × lower than a recently proposed photonic BNN accelerator, while a performance-efficient ROBIN design shows ∼3 × and ∼25 × better performance than electronic and photonic BNN accelerators, respectively. 
    more » « less
  5. ; ; (, IEEE)
    The increasing deployment of deep neural networks (DNNs) in cyber-physical systems (CPS) enhances perception fidelity, but imposes substantial computational demands on execution platforms, posing challenges to real-time control deadlines. Traditional distributed CPS architectures typically favor on-device inference to avoid network variability and contention-induced delays on remote platforms. However, this design choice places significant energy and computational demands on the local hardware. In this work, we revisit the assumption that cloud-based inference is intrinsically unsuitable for latency-sensitive control tasks. We demonstrate that, when provisioned with high-throughput compute resources, cloud platforms can effectively amortize network and queueing delays, enabling them to match or surpass on-device performance for real-time decision-making. Specifically, we develop a formal analytical model that characterizes distributed inference latency as a function of the sensing frequency, platform throughput, network delay, and task-specific safety constraints. We instantiate this model in the context of emergency braking for autonomous driving and validate it through extensive simulations using real-time vehicular dynamics. Our empirical results identify concrete conditions under which cloud-based inference adheres to safety margins more reliably than its on-device counterpart. These findings challenge prevailing design strategies and suggest that the cloud is not merely a feasible option, but often the preferred inference location for distributed CPS architectures. In this light, the cloud is not as distant as traditionally perceived; in fact, it is closer than it appears. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email