A graph-based feature selection method for learning to rank using spectral clustering for redundancy minimization and biased PageRank for relevance analysis.
Jen-Yuan YehCheng-Jung TsaiPublished in: Comput. Sci. Inf. Syst. (2022)
Keyphrases
- learning to rank
- spectral clustering
- information retrieval
- random walk
- query dependent
- graph laplacian
- graph partitioning
- feature vectors
- similarity matrix
- normalized cut
- clustering method
- link analysis
- ranking algorithm
- learning to rank algorithms
- ranking models
- directed graph
- information retrieval systems
- web search
- information extraction
- probabilistic model
- k means
- pairwise