raphaelsilva / Pixabay
Facebook has open sourced its deep learning recommendation model, or DLRM.
It announced from this post that “to help advance understanding in this subfield, we are open-sourcing a state-of-the-art deep learning recommendation model” that was implemented using Facebook’s open source PyTorch & Caffe2 platforms.
DLRM advances on other models by combining principles from both collaborative filtering & predictive analytics-based approaches, which enables it to work efficiently with production-scale data & provide state-of-art results.
Why has FB done so?
By releasing this model and also detailing its functionality here and in this accompanying paper, we hope to help the community find new ways to address to the unique challenges presented by this class of models. We also hope to encourage further algorithmic experimentation, modeling, system co-design, and benchmarking. This in turn will lead to new models and more efficient systems that can provide more relevant content to people using a wide range of digital services.
