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: Use Majority Voting
Tactic sort:
Awesome Tactic
Type: Architectural Tactic
Category: green-ml-enabled-systems
Title
Use Majority Voting
Description
Majority voting is a fusion method that avoids extra training overhead resulting in energy savings compared to a stacking/meta-model. Accuracy can also be improved.
Participant
Machine Learning Practitioners and Researchers.
Related software artifact
Fusion Method.
Context
Machine Learning Systems. Ensemble Fusion. Green AI.
Software feature
Majority Voting.
Tactic intent
Reduce energy and maintaining or improving accuracy.
Target quality attribute
Energy Efficiency.
Other related quality attributes
Accuracy.
Measured impact
Majority voting emerged as the more energy-efficient fusion method in comparison to meta-model. It not only required on average 34.43% less energy but also increased accuracy by 0.066. Energy measured in Joule (J) for training all base models, the optional meta-model, and fusion-time inference. Accuracy measured in F1.
Source
The More the Merrier? Navigating Accuracy vs. Energy Efficiency Design Trade-Offs in Ensemble Learning Systems by Rafiullah Omar et al. (DOI: https://doi.org/10.48550/arXiv.2407.02914)Graphical representation
