RETENTION: Resource-Efficient Tree-Based Ensemble Model Acceleration with Content-Addressable Memory

TL;DR

RETENTION introduces a resource-efficient framework that significantly reduces memory requirements for accelerating tree-based ensemble models using content-addressable memory, maintaining high accuracy.

Contribution

It proposes an iterative pruning algorithm and innovative data placement strategies to minimize CAM capacity for tree-based models, especially bagging-based ones.

Findings

CAM capacity reduced by up to 207x with less than 3% accuracy loss

Tree mapping scheme alone reduces CAM capacity by up to 21x

RETENTION achieves significant resource savings for tree model acceleration

Abstract

Although deep learning has demonstrated remarkable capability in learning from unstructured data, modern tree-based ensemble models remain superior in extracting relevant information and learning from structured datasets. While several efforts have been made to accelerate tree-based models, the inherent characteristics of the models pose significant challenges for conventional accelerators. Recent research leveraging content-addressable memory (CAM) offers a promising solution for accelerating tree-based models, yet existing designs suffer from excessive memory consumption and low utilization. This work addresses these challenges by introducing RETENTION, an end-to-end framework that significantly reduces CAM capacity requirement for tree-based model inference. We propose an iterative pruning algorithm with a novel pruning criterion tailored for bagging-based models (e.g., Random Forest), which minimizes model complexity while ensuring controlled accuracy degradation. Additionally, we present a tree mapping scheme that incorporates two innovative data placement strategies to alleviate the memory redundancy caused by the widespread use of don't care states in CAM. Experimental results show that implementing the tree mapping scheme alone reduces CAM capacity requirement by $1.46\times$ to $21.30 \times$, while the full RETENTION framework achieves $4.35\times$ to $207.12\times$ reduction with less than 3\% accuracy loss. These results demonstrate that RETENTION is highly effective in minimizing CAM resource demand, providing a resource-efficient direction for tree-based model acceleration.