Loading...
Please wait, while we are loading the content...
Similar Documents
Active Collaborative Prediction with Maximum Margin Matrix Factorization
| Content Provider | CiteSeerX |
|---|---|
| Abstract | Abstract — Collaborative prediction (CP) is a problem of predicting unobserved entries in sparsely observed matrices, e.g. product ratings by different users in online recommender systems. However, the quality of prediction may be quite sensitive to the choice of available samples, which motivates active sampling approaches. In this paper, we suggest an active sampling method based on the recently proposed Maximum-Margin Matrix Factorization (MMMF) [7], a linear factor model that was shown to outperform state-of-art collaborative prediction techniques. MMMF is formulated as a semidefinite program (SDP) that finds a low-norm (rather than traditional low-rank) matrix factorization, and is also closely related to learning max-margin linear discriminants (SVMs). This relation to SVMs inspires several margin-based active sampling heuristics that augment MMMF and demonstrate promising results in a variety of practical domains, including both traditional recommender systems and novel systems-management applications such as predicting latency and bandwidth in computer networks. I. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Unobserved Entry Active Sampling Approach Online Recommender System Linear Factor Model Observed Matrix Maximum-margin Matrix Factorization Matrix Factorization Active Sampling Method State-of-art Collaborative Prediction Technique Practical Domain Different User Available Sample Active Collaborative Prediction Max-margin Linear Discriminants Promising Result Product Rating Semidefinite Program Abstract Collaborative Prediction Novel Systems-management Application Several Margin-based Active Sampling Heuristic Maximum Margin Matrix Factorization Computer Network Traditional Recommender System |
| Content Type | Text |
| Resource Type | Article |
