An official website of the United States government
Resource is an important constraint when deploying Deep Neural Networks (DNNs) on mobile and edge devices. Existing works commonly adopt the cell-based search approach, which limits the flexibility of network patterns in learned cell structures. Moreover, due to the topology-agnostic nature of existing works, including both cell-based and node-based approaches, the search process is time consuming and the performance of found architecture may be sub-optimal. To address these problems, we propose AutoShrink, a topology-aware Neural Architecture Search (NAS) for searching efficient building blocks of neural architectures. Our method is node-based and thus can learn flexible network patterns in cell structures within a topological search space. Directed Acyclic Graphs (DAGs) are used to abstract DNN architectures and progressively optimize the cell structure through edge shrinking. As the search space intrinsically reduces as the edges are progressively shrunk, AutoShrink explores more flexible search space with even less search time. We evaluate AutoShrink on image classification and language tasks by crafting ShrinkCNN and ShrinkRNN models. ShrinkCNN is able to achieve up to 48% parameter reduction and save 34% Multiply-Accumulates (MACs) on ImageNet-1K with comparable accuracy of state-of-the-art (SOTA) models. Specifically, both ShrinkCNN and ShrinkRNN are crafted within 1.5 GPU hours, which is 7.2× and 6.7× faster than the crafting time of SOTA CNN and RNN models, respectively.
more »
« less
This content will become publicly available on December 18, 2025
HPC Application Parameter Autotuning on Edge Devices: A Bandit Learning Approach
The growing necessity for enhanced processing capabilities in edge devices with limited resources has led us to develop effective methods for improving high-performance computing (HPC) applications. In this paper, we introduce LASP (Lightweight Autotuning of Scientific Application Parameters), a novel strategy designed to address the parameter search space challenge in edge devices. Our strategy employs a multi-armed bandit (MAB) technique focused on online exploration and exploitation. Notably, LASP takes a dynamic approach, adapting seamlessly to changing environments. We tested LASP with four HPC applications: Lulesh, Kripke, Clomp, and Hypre. Its lightweight nature makes it particularly well-suited for resource-constrained edge devices. By employing the MAB framework to efficiently navigate the search space, we achieved significant performance improvements while adhering to the stringent computational limits of edge devices. Our experimental results demonstrate the effectiveness of LASP in optimizing parameter search on edge devices.
more »
« less
- PAR ID:
- 10627894
- Publisher / Repository:
- IEEE
- Date Published:
- ISBN:
- 979-8-3315-0909-5
- Page Range / eLocation ID:
- 12 to 22
- Format(s):
- Medium: X
- Location:
- Bangalore, India
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Resource is an important constraint when deploying Deep Neural Networks (DNNs) on mobile and edge devices. Existing works commonly adopt the cell-based search approach, which limits the flexibility of network patterns in learned cell structures. Moreover, due to the topology-agnostic nature of existing works, including both cell-based and node-based approaches, the search process is time consuming and the performance of found architecture may be sub-optimal. To address these problems, we propose AutoShrink, a topologyaware Neural Architecture Search (NAS) for searching efficient building blocks of neural architectures. Our method is node-based and thus can learn flexible network patterns in cell structures within a topological search space. Directed Acyclic Graphs (DAGs) are used to abstract DNN architectures and progressively optimize the cell structure through edge shrinking. As the search space intrinsically reduces as the edges are progressively shrunk, AutoShrink explores more flexible search space with even less search time. We evaluate AutoShrink on image classification and language tasks by crafting ShrinkCNN and ShrinkRNN models. ShrinkCNN is able to achieve up to 48% parameter reduction and save 34% Multiply-Accumulates (MACs) on ImageNet-1K with comparable accuracy of state-of-the-art (SOTA) models. Specifically, both ShrinkCNN and ShrinkRNN are crafted within 1.5 GPU hours, which is 7.2× and 6.7× faster than the crafting time of SOTA CNN and RNN models, respectively.more » « less
-
The increased ubiquitousness of small smart devices, such as cell- phones, tablets, smart watches and laptops, has led to unique user data, which can be locally processed. The sensors (e.g., microphones and webcam) and improved hardware of the new devices have al- lowed running deep learning models that 20 years ago would have been exclusive to high-end expensive machines. In spite of this progress, state-of-the-art algorithms for facial expression recognition (FER) rely on architectures that cannot be implemented on these devices due to computational and memory constraints. Alternatives involving cloud-based solutions impose privacy barriers that prevent their adoption or user acceptance in wide range of applications. This paper proposes a lightweight model that can run in real-time for image facial expression recognition (IFER) and video facial expression recognition (VFER). The approach relies on a personalization mechanism locally implemented for each subject by fine-tuning a central VFER model with unlabeled videos from a target subject. We train the IFER model to generate pseudo labels and we select the videos with the highest confident predictions to be used for adaptation. The adaptation is performed by implementing a federated learning strategy where the weights of the local model are averaged and used by the central VFER model. We demonstrate that this approach can improve not only the performance on the edge device providing personalized models to the users, but also the central VFER model. We implement a federated learning strategy where the weights of the local models are averaged and used by the central VFER. Within corpus and cross-corpus evaluations on two emotional databases demonstrate that edge models adapted with our personalization strategy achieve up to 13.1% gains in F1-scores. Furthermore, the federated learning implementation improves the mean micro F1-score of the central VFER model by up to 3.4%. The proposed lightweight solution is ideal for interactive user interfaces that preserve the data of the users.more » « less
-
As diverse high-performance computing (HPC) systems are built, many opportunities arise for applications to solve larger problems than ever before. Given the significantly increased complexity of these HPC systems and application tuning, empirical performance tuning, such as autotuning, has emerged as a promising approach in recent years. Despite its effectiveness, autotuning is often a computationally expensive approach. Transfer learning (TL)-based autotuning seeks to address this issue by leveraging the data from prior tuning. Current TL methods for autotuning spend significant time modeling the relationship between parameter configurations and performance, which is ineffective for few-shot (that is, few empirical evaluations) tuning on new tasks. We introduce the first generative TL-based autotuning approach based on the Gaussian copula (GC) to model the high-performing regions of the search space from prior data and then generate high-performing configurations for new tasks. This allows a sampling-based approach that maximizes few-shot performance and provides the first probabilistic estimation of the few-shot budget for effective TL-based autotuning. We compare our generative TL approach with state-of-the-art autotuning techniques on several benchmarks. We find that the GC is capable of achieving 64.37% of peak few-shot performance in its first evaluation. Furthermore, the GC model can determine a few-shot transfer budget that yields up to 33.39X speedup, a dramatic improvement over the 20.58X speedup using prior techniques.more » « less
-
Data volumes are exploding as sensors proliferate and become more capable. Edge computing is envisioned as a path to distribute processing and reduce latency. Many models of Edge computing consider small devices running conventional software. Our model includes a more lightweight execution engine for network microservices and a network scheduling framework to configure network processing elements to process streams and direct the appropriate traffic to them. In this article, we describe INDIANA, a complete framework for in-network microservices. We will describe how the two components-the INDIANA network Processing Element (InPE) and the Flange Network Operating System (NOS)-work together to achieve effective in-network processing to improve performance in edge to cloud environments. Our processing elements provide lightweight compute units optimized for efficient stream processing. These elements are customizable and vary in sophistication and resource consumption. The Flange NOS provides first-class flow based reasoning to drive function placement, network configuration, and load balancing that can respond dynamically to network conditions. We describe design considerations and discuss our approach and implementations. We evaluate the performance of stream processing and examine the performance of several exemplar applications on networks of increasing scale and complexity.more » « less
