All Tags
AWS
ai
algorithm-design
architecture
browser
cloud
cloud-efficiency
cloud-principles
cost-reduction
data-centric
data-compression
data-processing
deployment
design
documentation
edge-computing
email-sharing
energy-efficiency
energy-footprint
enterprise-optimization
green-ai
hardware
libraries
llm
locality
machine-learning
maintainability
management
measured
microservices
migration
mobile
model-optimization
model-training
multi-objective
network-traffic
parameter-tuning
performance
queries
rebuilding
scaling
services
storage-optimization
strategies
tabs
template
testing
workloads
Tactic: Consider Graph Substitution
Tactic sort:
Awesome Tactic
Type: Architectural Tactic
Category: green-ml-enabled-systems
Title
Consider Graph Substitution
Description
In the context of deep neural networks (DNN), graph substitution refers to replacing a large model with a smaller one that performs a similar task. Energy-aware graph substitution, however, means replacing energy-intensive nodes of deep neural networks with less energy-consuming nodes (Wang et al 2020).
Participant
Data Scientist
Related software artifact
Machine Learning Algorithm
Context
Machine Learning
Software feature
Neural Networks
Tactic intent
Improve energy efficiency by replacing energy-intensive nodes of DNNs with less energy-consuming nodes
Target quality attribute
Energy Efficiency
Other related quality attributes
Performance
Measured impact
Decreased energy consumption of 24% without a significant performance loss
Source
Yu Wang, Rong Ge, and Shuang Qiu. 2020. Energy-Aware DNN Graph Optimization. Resource-Constrained Machine Learning (ReCoML) Workshop of MLSys 2020 Conference (May 2020). arXiv:2005.05837 (DOI: https://doi.org/10.48550/arXiv.2005.05837)Graphical representation
