FusionAdvisor: Decision guidance for efficient operator fusion in deep models

As deep learning models grow in size and complexity, optimizing the execution efficiency becomes critical. Operator fusion merges multiple operators to reduce memory overhead and enhance computational efficiency. However, the combinatorial explosion of possible fusion combinations in modern models creates a search space that challenges traditional manual and heuristic methods. We propose FusionAdvisor, a neural network based framework that predicts the speedups of candidate fusion strategies from computation graphs and recommends the top- candidates (recommended strategies). Trained on our constructed fusion strategy dataset, it abstracts fusion selection as a service, enabling developers to choose high-performance strategies and accelerate inference efficiently. Experimental results demonstrate that FusionAdvisor’s neural network predicts post-fusion speedups with low error, enabling promising strategy recommendations while maintaining search efficiency comparable to the existing methods. This work advances automated operator fusion selection, reduces optimization costs, and improves resource utilization in complex scenarios, including Large Language Models (LLMs) and other large-scale models.

Authors

Publication Details

Journal
Big Data Mining and Analytics
Published
2026-11-20
DOI
https://doi.org/10.26599/bdma.2026.9020025
Primary Topic
Advanced Neural Network Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

FusionAdvisor: Decision guidance for efficient operator fusion in deep models

Jie Wu, Chang Jiang, Jianjiang Li, Yanan Yang et al.
6 links
Big Data Mining and Analytics
Advanced Neural Network Applications
article

FusionAdvisor: Decision guidance for efficient operator fusion in deep models

Jie Wu, Chang Jiang, Jianjiang Li, Yanan Yang, Shen Gao
article en

Abstract

As deep learning models grow in size and complexity, optimizing the execution efficiency becomes critical. Operator fusion merges multiple operators to reduce memory overhead and enhance computational efficiency. However, the combinatorial explosion of possible fusion combinations in modern models creates a search space that challenges traditional manual and heuristic methods. We propose FusionAdvisor, a neural network based framework that predicts the speedups of candidate fusion strategies from computation graphs and recommends the top- candidates (recommended strategies). Trained on our constructed fusion strategy dataset, it abstracts fusion selection as a service, enabling developers to choose high-performance strategies and accelerate inference efficiently. Experimental results demonstrate that FusionAdvisor’s neural network predicts post-fusion speedups with low error, enabling promising strategy recommendations while maintaining search efficiency comparable to the existing methods. This work advances automated operator fusion selection, reduces optimization costs, and improves resource utilization in complex scenarios, including Large Language Models (LLMs) and other large-scale models.

Big Data Mining and Analytics
Advanced Neural Network Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon