Deep Learning Recommendation Model for Personalization and Recommendation Systems
This work addresses a critical bottleneck in personalization and recommendation systems for improving scalability and efficiency, though it is incremental in advancing existing deep learning approaches.
The paper tackles the challenge of handling categorical features in neural network-based recommendation models by developing a deep learning recommendation model (DLRM) with a specialized parallelization scheme, demonstrating its state-of-the-art performance as a benchmark on the Big Basin AI platform.
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.