Скачать с ютуб apply(recsys) Conference 2022 | Real-Time Recommendation System With Collision-less Embedding Table в хорошем качестве

apply(recsys) Conference 2022 | Real-Time Recommendation System With Collision-less Embedding Table

apply(recsys) Conference 2022 | Monolith: Real-Time Recommendation System With Collision-less Embedding Table by: Youlong Cheng, Engineering Leader, ByteDance We’ll provide an introduction to Monolith, a system tailored for online training. Our design has been driven by observations of our application workloads and production environment that reflects a marked departure from other recommendations systems. Our contributions are manifold: first, we crafted a collisionless embedding table with optimizations such as expirable embeddings and frequency filtering to reduce its memory footprint; second, we provide an production-ready online training architecture with high fault-tolerance; finally, we proved that system reliability could be traded-off for real-time learning. Monolith has successfully landed in the BytePlus Recommend product. apply(): The ML data engineering Conference Presented by Tecton Connect with us: Slack: https://slack.feast.dev/ LinkedIn:   / tect.  .