RecIS: Sparse to Dense, A Unified Training Framework for Recommendation Models
By: Hua Zong , Qingtao Zeng , Zhengxiong Zhou and more
Potential Business Impact:
Helps online stores show you better stuff.
In this paper, we propose RecIS, a unified Sparse-Dense training framework designed to achieve two primary goals: 1. Unified Framework To create a Unified sparse-dense training framework based on the PyTorch ecosystem that meets the training needs of industrial-grade recommendation models that integrated with large models. 2.System Optimization To optimize the sparse component, offering superior efficiency over the TensorFlow-based recommendation models. The dense component, meanwhile, leverages existing optimization technologies within the PyTorch ecosystem. Currently, RecIS is being used in Alibaba for numerous large-model enhanced recommendation training tasks, and some traditional sparse models have also begun training in it.
Similar Papers
SCRec: A Scalable Computational Storage System with Statistical Sharding and Tensor-train Decomposition for Recommendation Models
Hardware Architecture
Makes online suggestions faster and use less power.
Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
Information Retrieval
Recommends better things by combining two ways of understanding.
DenseRec: Revisiting Dense Content Embeddings for Sequential Transformer-based Recommendation
Information Retrieval
Helps online stores suggest new items better.