Existing Collaborative Filtering Methods Research Articles

Enhanced knowledge transfer for collaborative filtering with multi-source heterogeneous feedbacks

Collaborative filtering (CF) is a widely used method in recommender systems due to its simplicity and efficiency. But most existing CF methods suffer from data scarcity, which arises from the situation with only a limited number of interactions between users and items. One solution to address is how to introduce Transfer Learning (TL)-based CF methods with heterogeneous feedbacks to deal with multi-source and heterogeneous data, such as rating vs. clicks or rating vs. purchase. However, in some applications, extremely sparse (i.e., sparsity level ≤ 0.1%) target data could cause under-transfer and negative transfer. To address the above issue, we propose an Enhanced Knowledge Transfer for Collaborative Filtering with Multi-Source Heterogeneous Feedbacks (EKT). Specifically, we first propose a weighted collective matrix tri-factorization framework. The proposed framework constrains the auxiliary data and the target data to share the same latent factors of users and items as well as partial cluster-level user-item rating pattern in order to enhance knowledge transfer and alleviate the under-transfer issue. Then, to alleviate the negative transfer issue, we integrate the graph co-regularization terms into a proposed framework, which contains the neighborhood structure information of users and items. At last, we simultaneously minimize the objective function of EKT, which consists of weighted collective matrix tri-factorization and the graph co-regularization of user and item graphs. Since the EKT framework is a non-convex optimization problem, we use an alternating optimization procedure to solve it and further prove its convergence. The experimental results on two benchmark datasets show that our proposed EKT method performs better than other baseline methods at almost all sparsity levels except for the denser case of 1% on ML10M and Netflix.

Web service QoS prediction: when collaborative filtering meets data fluctuating in big-range

Service recommendation aims to help users to find the most suitable Web services based on their quality of service (QoS) preferences instead of searching through extensive volume of Web services using search engine manually. Accurate unknown QoS rating prediction is one of the key challenges in the analysis of service recommendation. Collaborative filtering (CF) is a well-known recommendation method that estimates missing ratings by employing a set of similar users to the active user. The core idea of CF consists of picking out an appropriate set of users and using them in the rating prediction process. However, the majority of existing CF methods are not well-designed for Web service QoS prediction as they ignore the implicit but important characteristic of Web service QoS data that fluctuate in big-range. In other words, through analysis of real-world QoS datasets, we observed that QoS ratings vary widely and they are highly skewed with large variances, as two main facts, which dramatically degrade the accuracy of CF methods in QoS prediction. Towards this problem, in this paper, we propose a big-range aware collaborative filtering approach dubbed BRACF to predict Web service QoS ratings accurately. Specifically, since big-range of QoS data can lead to similarity exaggeration, we design a simple yet effective similarity model which considers the influence of big-range among users’ QoS data for accurately characterizing the similarity between users. Moreover, the similarity model is seamlessly incorporated into CF model for identifying similar neighbor using Top-K strategy and then it generates QoS predictions by combining bias information. Through extensive experiments on two public real-world Web service QoS for datasets, as response time and throughput, we show that BRACF significantly outperforms state-of-the-art CF methods. We believe that this work demonstrates the potential impact of big range data for the accurate QoS prediction.

Spatial-temporal data-driven service recommendation with privacy-preservation

The ever-increasing popularity of web service sharing communities have produced a considerable amount of web services that share similar functionalities but vary in Quality of Services (QoS) performances. To alleviate the heavy service selection burden on users, lightweight recommendation ideas, e.g., Collaborative Filtering (CF) have been developed to aid users to select their preferred services. However, existing CF methods often face two challenges. First, service QoS is often context-aware and hence depends on the spatial and temporal information of service invocations heavily. While it requires challenging efforts to integrate both spatial and temporal information into service recommendation decision-making process simultaneously. Second, the location-aware and time-aware QoS data often contain partial sensitive information of users, which raise an emergent privacy-preservation requirement when performing service recommendations. In view of above two challenges, in this paper, we integrate the spatial-temporal information of QoS data and Locality-Sensitive Hashing (LSH) into recommendation domain and bring forth a location-aware and time-aware recommendation approach considering privacy concerns. At last, a set of experiments conducted on well-known WS-DREAM dataset show the feasibility of our approach.

Contextual-boosted deep neural collaborative filtering model for interpretable recommendation

Collaborative filtering (CF) is one of the most successful recommendation techniques due to its simplicity and attractive accuracy. However, existing CF methods fail to interpret the reasons why they recommend a new item. In this paper, we propose a Contextual-boosted Deep Neural Collaborative filtering (CDNC) model for item recommendation, which simultaneously exploits both item introductions (textual features) and user ratings (collaborative features) to alleviate the cold-start problem and provide interpretable item recommendation. Specifically, we propose an interactive attention mechanism to learn the user representation, which makes use of the mutual information from both the user ratings and item introductions to supervise the representation learning of each other. With the learned attention weights, we can obtain the importance of each historical item among the historical list. Meanwhile, the attention model can assign different weights to the words in item introductions according to their importance. Therefore, CDNC can provide interpretations for the recommendations by assigning different attention weights to the historically interacted items and the words in the item introductions. On the other hand, we also learn the distributed representations of new-coming items with deep neural networks (i.e., LSTM), considering both rating and item introduction information. Finally, the user representation and the representations of new-coming item are concatenated to perform recommendation score prediction. Extensive experiments on four public benchmarks demonstrate the effectiveness of CDNC. In addition, CDNC has the advantage of interpreting the recommendations and providing user profiles for down-stream applications.

Improving Existing Collaborative Filtering Recommendations via Serendipity-Based Algorithm

In this paper, we study how to address the sparsity, accuracy and serendipity issues of top-N recommendation with collaborative filtering (CF). Existing studies commonly use rated items (which form only a small section in a rating matrix) or import some additional information (e.g., details about the items and users) to improve the performance of CF. Unlike these methods, we propose a novel notion towards a huge amount of unrated items: serendipity item. By utilizing serendipity items, we propose concise satisfaction and interest injection (CSII), a method that can effectively find interesting, satisfying, and serendipitous items in unrated items. By preventing uninteresting and unsatisfying items to be recommended as top-N items, this concise-but-novel method improves accuracy and recommendation quality (especially serendipity) substantially. Meanwhile, it can address the sparsity and cold-start issues by enriching the rating matrix in CF without additional information. As our method tackles rating matrix before recommendation procedure, it can be applied to most existing CF methods, such as item-based CF, user-based CF and matrix factorization-based CF. Through comprehensive experiments using abundant real-world datasets with LensKit implementation, we successfully demonstrate that our solution improves the performance of existing CF methods consistently and universally. Moreover, comparing with baseline methods, CSII can extract uninteresting items more carefully and cautiously, avoiding potential items inferred by mistake.

Collaborative filtering with weighted opinion aspects

Collaborative filtering (CF) aims to produce recommendations based on other users' ratings to an item. Most existing CF methods rely on the overall ratings an item has received. However, these ratings alone sometimes cannot provide sufficient information to understand users' behaviors. For example, a user giving a high rating may indicate that he loves the item as a whole; however, it is still likely that he dislikes some particular aspects at the same time. In addition, users tend to place different emphases on different aspects when reaching an overall rating. This emphasis on aspects may even vary from users to items, and has a significant impact on a user's final decision. To make a better understanding of a user' behavior and generate a more accurate recommendation, we propose a framework that incorporates both user opinions and preferences on different aspects. This framework is composed of three components, namely, an opinion mining component, an aspect weighting computing component, and a rating inference component. The first component exploits opinion mining techniques to extract and summarize opinions on multiple aspects from reviews, and generates ratings on various aspects. The second component applies a tensor factorization strategy to automatically infer weights of different aspects in reaching an overall rating. The last one infers the overall rating of an item based on both aspect ratings and weights. Experiments on two real datasets prove that our model performs better compared with the baseline methods.

Social Relations Model for Collaborative Filtering

We propose a novel probabilistic model for collaborative filtering (CF), called SRMCoFi, which seamlessly integrates both linear and bilinear random effects into a principled framework. The formulation of SRMCoFi is supported by both social psychological experiments and statistical theories. Not only can many existing CF methods be seen as special cases of SRMCoFi, but it also integrates their advantages while simultaneously overcoming their disadvantages. The solid theoretical foundation of SRMCoFi is further supported by promising empirical results obtained in extensive experiments using real CF data sets on movie ratings.

A hybrid collaborative filtering recommendation mechanism for P2P networks

With the increasing number of commerce facilities using peer-to-peer (P2P) networks, challenges exist in recommending interesting or useful products and services to a particular customer. Collaborative Filtering (CF) is one of the most successful techniques that attempts to recommend items (such as music, movies, web sites) which are likely to be of interest to the people. However, conventional collaborative filtering encounters a number of challenges on its recommendation accuracy. One of the most important challenges may be due to the sparse attributes inherent to the rating data. Another important challenge is that existing CF methods consider mainly user-based or item-based ratings respectively. In this paper a P2P-based hybrid collaborative filtering mechanism for the support of combining user-based and item attribute-based ratings is considered. We take advantage of the inherent item attributes to construct a Boolean matrix to predict the blank elements for a sparse user–item matrix. Furthermore, a Hybrid collaborative filtering (HCF) algorithm is presented to improve the predictive accuracy. Case studies and experiment results illustrate that our approaches not only contribute to predicting the unrated blank data for a sparse matrix but also improve the prediction accuracy as expected.