Extreme Learning to Rank via Low Rank Assumption
[edit]
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:951960, 2018.
Abstract
We consider the setting where we wish to perform ranking for hundreds of thousands of users which is common in recommender systems and web search ranking. Learning a single ranking function is unlikely to capture the variability across all users while learning a ranking function for each person is timeconsuming and requires large amounts of data from each user. To address this situation, we propose a Factorization RankSVM algorithm which learns a series of k basic ranking functions and then constructs for each user a local ranking function that is a combination of them. We develop a fast algorithm to reduce the time complexity of gradient descent solver by exploiting the lowrank structure, and the resulting algorithm is much faster than existing methods. Furthermore, we prove that the generalization error of the proposed method can be significantly better than training individual RankSVMs. Finally, we present some interesting patterns in the principal ranking functions learned by our algorithms.
Related Material


