Collaborative filtering based on multi-channel diffusion

Shang, Mingsheng; Jin, Ci-Hang; Zhou, Tao; Zhang, Yicheng

doi:10.1016/j.physa.2009.08.011

Cited by 23 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So that if a user i has collected an object α with rating 2, her will only connect to α (2) . After that, one can directly apply the probabilistic spreading process (see the next subsection) to obtain the similarity and then integrate it into the collaborative filtering framework to obtain better recommendation [196].…”

Section: Multilevel Spreading Algorithm (Multis)mentioning

confidence: 99%

Recommender systems

et al. 2012

Self Cite

View full text Add to dashboard Cite

The ongoing rapid expansion of the Internet greatly increases the necessity of effective recommender systems for filtering the abundant information. Extensive research for recommender systems is conducted by a broad range of communities including social and computer scientists, physicists, and interdisciplinary researchers. Despite substantial theoretical and practical achievements, unification and comparison of different approaches are lacking, which impedes further advances. In this article, we review recent developments in recommender systems and discuss the major challenges. We compare and evaluate available algorithms and examine their roles in the future developments. In addition to algorithms, physical aspects are described to illustrate macroscopic behavior of recommender systems. Potential impacts and future directions are discussed. We emphasize that recommendation has a great scientific depth and combines diverse research fields which makes it of interests for physicists as well as interdisciplinary researchers.

show abstract

Section: Multilevel Spreading Algorithm (Multis)mentioning

confidence: 99%

Recommender systems

et al. 2012

Self Cite

View full text Add to dashboard Cite

show abstract

“…The related CF and interdisciplinary algorithms have already been successfully applied to many well-known recommendation platforms. Meanwhile, many recent works have been devoted to study the expansion of both algorithms, for instance hybrid method [148,149], biased-heat conduction [150,151], multi-channel diffusion [152], preferential diffusion [45,46], hybrid diffusion [47], direct random walks method based on CF [153], hypergraph model with social tag [154,155], multilinear interactive matrix factorization [156]. These algorithms would further improve the efficiency of the recommendation.…”

Section: Link Prediction In Bipartite Network For Recommendationmentioning

confidence: 99%

Structure-oriented prediction in complex networks

2018

Self Cite

View full text Add to dashboard Cite

Complex systems are extremely hard to predict due to its highly nonlinear interactions and rich emergent properties. Thanks to the rapid development of network science, our understanding of the structure of real complex systems and the dynamics on them has been remarkably deepened, which meanwhile largely stimulates the growth of effective prediction approaches on these systems. In this article, we aim to review different networkrelated prediction problems, summarize and classify relevant prediction methods, analyze their advantages and disadvantages, and point out the forefront as well as critical challenges of the field. Contents

show abstract

“…Meanwhile, many recent works have been devoted to study the expansion of both algorithms, for instance hybrid method [25,26], biased-heat conduction [27,28], multi-channel diffusion [29], preferential diffusion [30,31], hybrid diffusion [32], direct random walks method based on CF [33], hypergraph model with social tag [34,35], multi-linear interactive matrix factorization [36]. These algorithms would further improve the efficiency of the information filtering.…”

Section: Introductionmentioning

confidence: 99%

A generalized model via random walks for information filtering

et al. 2016

Self Cite

View full text Add to dashboard Cite

There could exist a simple general mechanism lurking beneath collaborative filtering and interdisciplinary physics approaches which have been successfully applied to online E-commerce platforms. Motivated by this idea, we propose a generalized model employing the dynamics of the random walk in the bipartite networks. Taking into account the degree information, the proposed generalized model could deduce the collaborative filtering, interdisciplinary physics approaches and even the enormous expansion of them. Furthermore, we analyze the generalized model with single and hybrid of degree information on the process of random walk in bipartite networks, and propose a possible strategy by using the hybrid degree information for different popular objects to toward promising precision of the recommendation.

show abstract

Collaborative filtering based on multi-channel diffusion

Cited by 23 publications

References 31 publications

Recommender systems

Recommender systems

Structure-oriented prediction in complex networks

A generalized model via random walks for information filtering

Contact Info

Product

Resources

About