Scalable Exploration for Neural Online Learning to Rank with Perturbed Feedback.
Yiling JiaHongning WangPublished in: CoRR (2022)
Keyphrases
- learning to rank
- balancing exploration and exploitation
- user feedback
- ranking functions
- information retrieval
- loss function
- reinforcement learning
- document retrieval
- collaborative filtering
- evaluation measures
- ranking svm
- learning to rank algorithms
- direct optimization
- test collection
- evaluation metrics
- relevance judgments
- query dependent
- retrieval systems
- support vector
- web search engines
- pairwise
- learning algorithm