Lessons Learnt From Consolidating ML Models in a Large Scale Recommendation System
Paper · Source
Synthesis notes from this paper's topics
This paper has no direct semantic matches yet — here are notes from the topic(s) it's filed under.
- Can simpler models beat deep networks for recommendation systems?
- Can a linear model beat deep collaborative filtering?
- Do LLM explanations faithfully describe their recommendation process?
- Can we distill LLM knowledge into graphs for real-time recommendations?
- Can MLPs learn to match dot product similarity in practice?
- Why does dot product beat MLP-based similarity in practice?
- Why does Netflix use multiple ranking systems instead of one?
- What does Netflix need to optimize in those first 90 seconds?