Link prediction approach to collaborative filtering

By Zan Huang, Xin Li, Hsinchun Chen. ACM/IEEE Joint Conference on Digital Libraries, 2005

465 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/5257c7ddcf1d0b51596524eea9f54942f124e0ec

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Statistical and Nonlinear Physics

Citations in the corpus

Link Prediction via Matrix Factorization (2011, background): “Despite this connection, there has been limited interaction between the link prediction and collaborative filtering literatures, aside from a few papers that propose to solve one problem using models from the other [7,23].”
Predicting missing links via local information (2009, unknown): “which has already been suggested as a proximity measure [43], as well as been used to quantify the functional significance of links subject to various network-based dynamics, such as percolation [44], synchronization [45] and transportation [46].”
A Survey of Link Prediction in Social Networks (2011, background): “In e-commerce, one of the most prominent usages of link prediction is to build recommendation systems [25, 37, 35].”
Human mobility, social ties, and link prediction (2011, methodology): “Existing approaches have focused on defining various proximity measures on network topology, to serve as predictors of new links in both supervised [2, 31, 23, 15] and unsupervised [21] frameworks.”
Temporal Link Prediction Using Matrix and Tensor Factorizations (2010, methodology): “Next, we consider the Katz method [Katz 1953] (extended to bipartite graphs), which has proven to be highly accurate in previous work on link prediction [Huang et al. 2005; Huang and Lin 2009; Liben-Nowell and Kleinberg 2007]; however, it is not always clear how to make the method scalable.”
Link prediction in weighted networks: The role of weak ties (2010, background): “Recently, the link prediction in complex networks has attracted increasing attention from computer scientists [6,7] and physicists [8,9].”
Fast Incremental and Personalized PageRank (2010, unknown): “Collaborative ﬁltering on social networks is very closely related to the Link Prediction problem [1,12,17,18,31,42], for which the random walk based methods have been re-ported to work very well [31] (we also veriﬁed this experimentally; the results are given in Appendix A).”
Recommender Systems (2016, unknown): “For example, the ItemRank method proposed in [232] shows how to use ranking directly to make predictions, and the method in [261] shows how to use link-prediction methods directly for collaborative filtering.”
Link Prediction in Complex Networks: A Survey (2010, methodology): “In addition, the similarities can be used in a more skilled way, such as being locally integrated under the collaborative filtering5 framework [34].”
Link prediction using supervised learning (2006, background): “Several recent initiatives [17, 14 , 15] have studied network topological features for dieren t application areas, like link analysis, collaborative ltering, etc.”
A Survey of Link Prediction in Complex Networks (2016, background): “[2003]), a neural network of Caenorhabditis elegans (CEL, Watts and Strogatz [1998]), a network describing face-to-face contacts of people during the exhibition Infectious: Stay Away in 2009 at the Science Gallery in Dublin (INF, Isella et al. [2011]), a frequent copurchasing network of books about ”
Protecting privacy when mining and sharing user data (2012, background): “Suggestions for graph link-analysis based utility functions include: number of common neighbors, number of weighted paths, and PageRank distributions [87,122,163].”