Ihas: Instance-Wise Hierarchical Architecture Search for Deep Learning Recommendation Models

By Yakun Yu et al

Published on June 10, 2023

Read the original document by opening this link in a new tab.

Table of Contents

1. Introduction
2. Related Work
3. Method
3.1 Overview
3.2 Deep Learning Recommender Models
3.3 Bernoulli Gates
4. Experimental Results
5. Conclusion

Summary

The document discusses iHAS, a framework for automatic architecture search at the instance level for recommender systems. It introduces three stages: searching, clustering, and retraining to optimize neural architecture based on instance-wise embedding dimensions. The paper highlights the effectiveness of iHAS in improving recommendation models' performance and transferability to diverse deep recommender models.