Direct Optimization of Ranking Measures
arXiv:0704.3359
Abstract
Web page ranking and collaborative filtering require the optimization of sophisticated performance measures. Current Support Vector approaches are unable to optimize them directly and focus on pairwise comparisons instead. We present a new approach which allows direct optimization of the relevant loss functions. This is achieved via structured estimation in Hilbert spaces. It is most related to Max-Margin-Markov networks optimization of multivariate performance measures. Key to our approach is that during training the ranking problem can be viewed as a linear assignment problem, which can be solved by the Hungarian Marriage algorithm. At test time, a sort operation is sufficient, as our algorithm assigns a relevance score to every (document, query) pair. Experiments show that the our algorithm is fast and that it works very well.
References in corpus (1)
Cited by in corpus (16)
- VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
- Ranking via Sinkhorn Propagation
- A Feature Selection Method for Multivariate Performance Measures
- Top Rank Optimization in Linear Time
- Word2Vec applied to Recommendation: Hyperparameters Matter
- Surrogate Functions for Maximizing Precision at the Top
- Exponential Family Graph Matching and Ranking
- Learning to Predict Combinatorial Structures
- Ranking via Robust Binary Classification and Parallel Parameter Estimation in Large-Scale Data
- Accelerated learning from recommender systems using multi-armed bandit
- Latent Structured Ranking
- Optimize What You Evaluate With: A Simple Yet Effective Framework For Direct Optimization Of IR Metrics
- Analysis of Regression Tree Fitting Algorithms in Learning to Rank
- Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts
- Training Efficiency and Robustness in Deep Learning
- Using Deep Cross Modal Hashing and Error Correcting Codes for Improving the Efficiency of Attribute Guided Facial Image Retrieval