Abstract | ||
---|---|---|
Recently, learning to rank, which aims at constructing a model for ranking objects, is one of the hot research topics in information retrieval and machine learning communities. Most of existing learning to rank approaches are based on the assumption that each object is independently and identically distributed. Although this assumption simplifies ranking problems, the implicit interconnections between objects are ignored. In this paper, a graph based ranking framework is proposed, which takes advantage of implicit correlations between objects. Furthermore, the derived relational ranking algorithm from this framework, called GRSVM, is developed based on the conventional algorithm RankSVM-primal. In addition, generalization properties of different relational ranking algorithms are analyzed using Rademacher Average. Based on the analysis, we find that GRSVM can achieve tighter generalization bound than existing relational ranking algorithms in most cases. Finally, a comparison of experimental results produced by improved and conventional algorithms shows the superior performance of the former. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1142/S0218213012500212 | INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS |
Keywords | Field | DocType |
Learning to rank, global consistency, generalization bound, Rademacher Average | Learning to rank,Graph,Ranking SVM,Ranking,Pattern recognition,Computer science,Ranking (information retrieval),Artificial intelligence,Independent and identically distributed random variables,Global consistency,Machine learning | Journal |
Volume | Issue | ISSN |
21 | 3 | 0218-2130 |
Citations | PageRank | References |
0 | 0.34 | 21 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zewu Peng | 1 | 1 | 0.68 |
Yan Pan | 2 | 179 | 19.23 |
Yong Tang | 3 | 554 | 76.46 |
Guohua Chen | 4 | 0 | 0.34 |