Towards Automated Model Design on Recommender Systems
Automated model design approaches for recommender systems using neural architecture search and optimization techniques.
Tunhou zhang
•
•
1 min read
Farthest Greedy Path Sampling for Two-shot Recommender Search
We introduce Farthest Greedy Path Sampling (FGPS) for Two-shot Neural Architecture Search (TS-NAS) in recommender systems, achieving state-of-the-art performance on CTR prediction …
Yufan cao