Practicalizing Tree-Based Model Acceleration with CAM through Model Pruning and Data Placement Optimization

Tree-based model remains state-of-the-art for many tasks involving tabular data. While these models are favored in resource-constrained environments, the inherent characteristics result in inefficiency during inference, posing significant challenges for conventional accelerators. Recent research has achieved unprecedented acceleration with content-addressable memory (CAM), yet at the cost of overwhelming memory consumption with low utilization, which is impractical for numerous real-world applications. This work addresses these issues by introducing an end-to-end framework RETENTION. RETENTION incorporates (1) a pruning algorithm to minimize model complexity under a user-specified accuracy loss tolerance, and (2) two data placement strategies to enhance memory utilization and further reduce capacity requirement. Experiment results show that space efficiency can be improved from 4.35× to 207.12× with less than 3% accuracy loss.

Authors

Institutions

Publication Details

Published
2025-09-28
DOI
https://doi.org/10.1145/3742873.3758342
Primary Topic
Network Packet Processing and Optimization
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Practicalizing Tree-Based Model Acceleration with CAM through Model Pruning and Data Placement Optimization

Camélia Slimani, Yi-Chun Liao, Jalil Boukhobza, Tei‐Wei Kuo et al.
Network Packet Processing and Optimization
article

Practicalizing Tree-Based Model Acceleration with CAM through Model Pruning and Data Placement Optimization

Camélia Slimani, Yi-Chun Liao, Jalil Boukhobza, Tei‐Wei Kuo, Yuan-Hao Chang, Chieh-Lin Tsai
article en

Abstract

Tree-based model remains state-of-the-art for many tasks involving tabular data. While these models are favored in resource-constrained environments, the inherent characteristics result in inefficiency during inference, posing significant challenges for conventional accelerators. Recent research has achieved unprecedented acceleration with content-addressable memory (CAM), yet at the cost of overwhelming memory consumption with low utilization, which is impractical for numerous real-world applications. This work addresses these issues by introducing an end-to-end framework RETENTION. RETENTION incorporates (1) a pruning algorithm to minimize model complexity under a user-specified accuracy loss tolerance, and (2) two data placement strategies to enhance memory utilization and further reduce capacity requirement. Experiment results show that space efficiency can be improved from 4.35× to 207.12× with less than 3% accuracy loss.

Centre National de la Recherche Scientifique (FR), University of California, Santa Barbara (US), Université de Bretagne Occidentale (FR), National Taiwan University (TW), École Nationale Supérieure de Techniques Avancées (FR), Institut National Polytechnique de Toulouse (FR), Laboratoire des Sciences et Techniques de l’Information de la Communication et de la Connaissance (FR), Delta Electronics (Taiwan) (TW), École nationale supérieure de techniques avancées Bretagne (FR), École Nationale Supérieure d'Électrotechnique, d'Électronique, d'Informatique, d'Hydraulique et des Télécommunications (FR), École Nationale Supérieure de Techniques Avancées Paris (FR), Korea Institute of Science & Technology Information (KR)
Openalex Percentile: Top 56%
Network Packet Processing and Optimization
DOIOpen Access PDFOpenAlex
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.