paper-with-me

Papers

Energy-Aware DNN Graph Optimization

2020-05-12 · Yu Wang, Rong Ge, Shuang Qiu

Unlike existing work in deep neural network (DNN) graphs optimization for inference performance, we explore DNN graph optimization for energy awareness and savings for power- and resource-constrained machine learning devices. We present a method that allows users to optimize energy consumption or balance between energy and inference performance for DNN graphs. This method efficiently searches through the space of equivalent graphs, and identifies a graph and the corresponding algorithms that incur the least cost in execution. We implement the method and evaluate it with multiple DNN models on a GPU-based machine. Results show that our method achieves significant energy savings, i.e., 24% with negligible performance impact.

📄 PDF Abstract BibTeX arXiv:2005.05837

Code (1)

wangyu-/mlsys20_workshop 공식 구현

Tasks

GPU

Similar Papers 제목 키워드 기반

Descent Steps of a Relation-Aware Energy Produce Heterogeneous Graph Neural Networks

2022-06-22 · Hongjoon Ahn, Yongyi Yang, Quan Gan, Taesup Moon 외

Heterogeneous graph neural networks (GNNs) achieve strong performance on node classification tasks in a semi-supervised learning setting. However, as in the simpler homogeneous GNN case, message-passing-based heterogeneo…

Bilevel OptimizationClassificationNode ClassificationRelation

Energy-Efficient Dynamic Training and Inference for GNN-Based Network Modeling

2025-03-24 · Chetna Singhal, Yassine Hadjadj-Aoul

Efficient network modeling is essential for resource optimization and network planning in next-generation large-scale complex networks. Traditional approaches, such as queuing theory-based modeling and packet-based simul…

EnergyMamba: An Uncertainty-Aware Graph-Enhanced Selective State Space Model for Energy Consumption Prediction

2026-05-30 · Dahai Yu, Rongchao Xu, Lin Jiang, Guang Wang arxiv

Energy consumption prediction is essential for efficient grid management, demand-side optimization, and sustainable energy planning. Although advanced machine learning methods have been employed for better prediction per…

AUGUR, A flexible and efficient optimization algorithm for identification of optimal adsorption sites

2024-09-24 · Ioannis Kouroudis, Poonam, Neel Misciaci, Felix Mayr 외

In this paper, we propose a novel flexible optimization pipeline for determining the optimal adsorption sites, named AUGUR (Aware of Uncertainty Graph Unit Regression). Our model combines graph neural networks and Gaussi…

Bayesian OptimizationGaussian ProcessesUncertainty Quantification

Energy-Aware UAV-Enabled Target Tracking: Online Optimization with Location Constraints

2024-07-17 · Yifan Jiang, Qingqing Wu, Wen Chen, Hongxun Hui

For unmanned aerial vehicle (UAV) trajectory design, the total propulsion energy consumption and initial-final location constraints are practical factors to consider. However, unlike traditional offline designs, these tw…