Deep Learning Recommendation Model for Personalization and Recommendation Systems

TL;DR

This paper introduces a state-of-the-art deep learning recommendation model (DLRM) designed for personalization tasks, addressing challenges with categorical features, and demonstrates its scalability and effectiveness as a benchmark.

Contribution

The paper develops DLRM with a novel parallelization scheme and provides implementations in PyTorch and Caffe2, advancing recommendation system research.

Findings

DLRM outperforms existing models on benchmark tasks.

The specialized parallelization scheme effectively scales training.

DLRM serves as a useful benchmark for future research.

Abstract

With the advent of deep learning, neural network-based recommendation models have emerged as an important tool for tackling personalization and recommendation tasks. These networks differ significantly from other deep learning networks due to their need to handle categorical features and are not well studied or understood. In this paper, we develop a state-of-the-art deep learning recommendation model (DLRM) and provide its implementation in both PyTorch and Caffe2 frameworks. In addition, we design a specialized parallelization scheme utilizing model parallelism on the embedding tables to mitigate memory constraints while exploiting data parallelism to scale-out compute from the fully-connected layers. We compare DLRM against existing recommendation models and characterize its performance on the Big Basin AI platform, demonstrating its usefulness as a benchmark for future algorithmic experimentation and system co-design.