Developing a Recommendation Benchmark for MLPerf Training and Inference
This work addresses the need for standardized benchmarks in recommendation systems, which are crucial for large-scale AI inference in datacenters, but it is incremental as it builds on existing MLPerf frameworks.
The paper tackled the lack of performance exploration in deep learning-based recommendation models by defining an industry-relevant recommendation benchmark for MLPerf Training and Inference Suites, synthesizing modeling strategies and characteristics for personalized recommendation systems.
Deep learning-based recommendation models are used pervasively and broadly, for example, to recommend movies, products, or other information most relevant to users, in order to enhance the user experience. Among various application domains which have received significant industry and academia research attention, such as image classification, object detection, language and speech translation, the performance of deep learning-based recommendation models is less well explored, even though recommendation tasks unarguably represent significant AI inference cycles at large-scale datacenter fleets. To advance the state of understanding and enable machine learning system development and optimization for the commerce domain, we aim to define an industry-relevant recommendation benchmark for the MLPerf Training andInference Suites. The paper synthesizes the desirable modeling strategies for personalized recommendation systems. We lay out desirable characteristics of recommendation model architectures and data sets. We then summarize the discussions and advice from the MLPerf Recommendation Advisory Board.