CAME: Competitively Learning a Mixture-of-Experts Model for First-stage Retrieval.
Yinqiong CaiYixing FanKeping BiJiafeng GuoWei ChenRuqing ZhangXueqi ChengPublished in: CoRR (2023)
Keyphrases
- mathematical model
- prior knowledge
- learning scheme
- online learning
- learning systems
- computational model
- neural network
- high level
- learning models
- management system
- learning tasks
- parameter estimation
- latent variable models
- learning mechanism
- experimental data
- statistical model
- mixture model
- supervised learning
- probability distribution
- active learning
- objective function
- search engine