Previous work on the one-class collaborative filtering （OCCF） problem can be roughly categorized into pointwise methods, pairwise methods, and content-based methods. A fundamental assumption of these approaches is t...Previous work on the one-class collaborative filtering （OCCF） problem can be roughly categorized into pointwise methods, pairwise methods, and content-based methods. A fundamental assumption of these approaches is that all missing values in the user-item rating matrix are considered negative. However, this assumption may not hold because the missing values may contain negative and positive examples. For example, a user who fails to give positive feedback about an item may not necessarily dislike it; he may simply be unfamiliar with it. Meanwhile, content-based methods, e.g. collaborative topic regression （CTR）, usually require textual content information of the items, and thus their applicability is largely limited when the text information is not available. In this paper, we propose to apply the latent Dirichlet allocation （LDA） model on OCCF to address the above-mentioned problems. The basic idea of this approach is that items are regarded as words, users are considered as documents, and the user-item feedback matrix constitutes the corpus. Our model drops the strong assumption that missing values are all negative and only utilizes the observed data to predict a user＇s interest. Additionally, the proposed model does not need content information of the items. Experimental results indicate that the proposed method outperforms previous methods on various ranking-oriented evaluation metrics.We further combine this method with a matrix factorizationbased method to tackle the multi-class collaborative filtering （MCCF） problem, which also achieves better performance on predicting user ratings.展开更多
基金We greatly appreciate Weike Pan for his codes of algorithm GBPR[1], which makes us able to evaluate the algorithm more efficiently and more fairly. This work was supported by the National Natural Science Foundation of China （NSFC） （Grant Nos. 61370126, 61672081, 71540028, 61571052, 61602237）, National High-tech R＆D Program of China （2015AA016004）, Beijing Advanced Innovation Center for Imaging Technology （BAICIT-2016001）, the Fund of the State Key Laboratory of Software Development Environment （SKLSDE-2013ZX-19）, the Fund of Beijing Social Science （14JGC103）, the Statistics Research Project of National Bureau （2013LY055）, and the Fund of Beijing Wuzi University, China （GJB20141002）.
文摘Previous work on the one-class collaborative filtering （OCCF） problem can be roughly categorized into pointwise methods, pairwise methods, and content-based methods. A fundamental assumption of these approaches is that all missing values in the user-item rating matrix are considered negative. However, this assumption may not hold because the missing values may contain negative and positive examples. For example, a user who fails to give positive feedback about an item may not necessarily dislike it; he may simply be unfamiliar with it. Meanwhile, content-based methods, e.g. collaborative topic regression （CTR）, usually require textual content information of the items, and thus their applicability is largely limited when the text information is not available. In this paper, we propose to apply the latent Dirichlet allocation （LDA） model on OCCF to address the above-mentioned problems. The basic idea of this approach is that items are regarded as words, users are considered as documents, and the user-item feedback matrix constitutes the corpus. Our model drops the strong assumption that missing values are all negative and only utilizes the observed data to predict a user＇s interest. Additionally, the proposed model does not need content information of the items. Experimental results indicate that the proposed method outperforms previous methods on various ranking-oriented evaluation metrics.We further combine this method with a matrix factorizationbased method to tackle the multi-class collaborative filtering （MCCF） problem, which also achieves better performance on predicting user ratings.
