Recommendation as link prediction in bipartite graphs: A graph kernel-based machine learning approach

Recommender systems have been widely adopted in online applications to suggest products, services, and contents to potential users. Collaborative filtering (CF) is a successful recommendation paradigm that employs transaction information to enrich user and item features for recommendation. By mappin...

Full description

Saved in:
Bibliographic Details
Published in:Decision Support Systems Vol. 54; no. 2; pp. 880 - 890
Main Authors: Li, Xin, Chen, Hsinchun
Format: Journal Article
Language:English
Published: Amsterdam Elsevier B.V 01.01.2013
Elsevier
Elsevier Sequoia S.A
Subjects:
Algorithms
Applied sciences
Artificial intelligence
Bipartite graph
Collaborative filtering
Computer science; control theory; systems
Computer systems and distributed systems. User interface
Decision support systems
Enrichment
Exact sciences and technology
Filtering
Filtration
Firm modelling
Graph representations
Graphs
Kernel-based methods
Kernels
Learning and adaptive systems
Link prediction
Links
Mapping
Markov processes
Mathematics
Operational research and scientific management
Operational research. Management science
Probability and statistics
Probability theory and stochastic processes
Random walk
Recommender systems
Sciences and techniques of general use
Software
Studies
Link prediction
Bipartite graph
Collaborative filtering
Kernel-based methods
Recommender systems
Content access
Random walk
Graph theory
Transaction processing
Recommendation
Kernel method
Graph connectivity
User interface
Learning (artificial intelligence)
Information structure
Learning algorithm
Artificial intelligence
Binary classification
Service economy
Molecular computation
ISSN:0167-9236, 1873-5797
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recommender systems have been widely adopted in online applications to suggest products, services, and contents to potential users. Collaborative filtering (CF) is a successful recommendation paradigm that employs transaction information to enrich user and item features for recommendation. By mapping transactions to a bipartite user–item interaction graph, a recommendation problem is converted into a link prediction problem, where the graph structure captures subtle information on relations between users and items. To take advantage of the structure of this graph, we propose a kernel-based recommendation approach and design a novel graph kernel that inspects customers and items (indirectly) related to the focal user–item pair as its context to predict whether there may be a link. In the graph kernel, we generate random walk paths starting from a focal user–item pair and define similarities between user–item pairs based on the random walk paths. We prove the validity of the kernel and apply it in a one-class classification framework for recommendation. We evaluate the proposed approach with three real-world datasets. Our proposed method outperforms state-of-the-art benchmark algorithms, particularly when recommending a large number of items. The experiments show the necessity of capturing user–item graph structure in recommendation. ► We propose a kernel-based approach for link prediction and recommendation. ► We design a graph kernel to exploit features in the context of focal user–item pair. ► The kernel works with a one-class SVM algorithm to predict user–item interactions. ► We prove the validity and computational efficiency of the graph kernel. ► Our model outperforms benchmarks, particularly for large amounts of recommendations.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0167-9236
1873-5797
DOI:10.1016/j.dss.2012.09.019