Constructing compact and effective graphs for recommender systems via node and edge aggregations
Abstract
Exploiting graphs for recommender systems has great potential to flexibly incorporate heterogeneous information for producing better recommendation results. As our baseline approach, we first introduce a naive graph-based recommendation method, which operates with a heterogeneous log-metadata graph constructed from user log and content metadata databases. Although the na ve graph-based recommendation method is simple, it allows us to take advantages of heterogeneous information and shows promising flexibility and recommendation accuracy. However, it often leads to extensive processing time due to the sheer size of the graphs constructed from entire user log and content metadata databases. In this paper, we propose node and edge aggregation approaches to constructing compact and e ective graphs called Factor-Item bipartite graphs by aggregating nodes and edges of a log-metadata graph. Furthermore, experimental results using real world datasets indicate that our approach can significantly reduce the size of graphs exploited for recommender systems without sacrificing the recommendation quality.
- Authors:
-
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Georgia Institute of Technology, Atlanta, GA (United States)
- Seoul National Univ. (Republic of Korea)
- Publication Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE Laboratory Directed Research and Development (LDRD) Program
- OSTI Identifier:
- 1185808
- Alternate Identifier(s):
- OSTI ID: 1437067
- Grant/Contract Number:
- AC05-00OR22725
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Expert Systems with Applications
- Additional Journal Information:
- Journal Volume: 42; Journal Issue: 7; Journal ID: ISSN 0957-4174
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; graph; heterogeneity; recommendation; aggregation; random-walk; ranking
Citation Formats
Lee, Sangkeun, Kahng, Minsuk, and Lee, Sang-goo. Constructing compact and effective graphs for recommender systems via node and edge aggregations. United States: N. p., 2014.
Web. doi:10.1016/j.eswa.2014.11.062.
Lee, Sangkeun, Kahng, Minsuk, & Lee, Sang-goo. Constructing compact and effective graphs for recommender systems via node and edge aggregations. United States. https://doi.org/10.1016/j.eswa.2014.11.062
Lee, Sangkeun, Kahng, Minsuk, and Lee, Sang-goo. Wed .
"Constructing compact and effective graphs for recommender systems via node and edge aggregations". United States. https://doi.org/10.1016/j.eswa.2014.11.062. https://www.osti.gov/servlets/purl/1185808.
@article{osti_1185808,
title = {Constructing compact and effective graphs for recommender systems via node and edge aggregations},
author = {Lee, Sangkeun and Kahng, Minsuk and Lee, Sang-goo},
abstractNote = {Exploiting graphs for recommender systems has great potential to flexibly incorporate heterogeneous information for producing better recommendation results. As our baseline approach, we first introduce a naive graph-based recommendation method, which operates with a heterogeneous log-metadata graph constructed from user log and content metadata databases. Although the na ve graph-based recommendation method is simple, it allows us to take advantages of heterogeneous information and shows promising flexibility and recommendation accuracy. However, it often leads to extensive processing time due to the sheer size of the graphs constructed from entire user log and content metadata databases. In this paper, we propose node and edge aggregation approaches to constructing compact and e ective graphs called Factor-Item bipartite graphs by aggregating nodes and edges of a log-metadata graph. Furthermore, experimental results using real world datasets indicate that our approach can significantly reduce the size of graphs exploited for recommender systems without sacrificing the recommendation quality.},
doi = {10.1016/j.eswa.2014.11.062},
journal = {Expert Systems with Applications},
number = 7,
volume = 42,
place = {United States},
year = {Wed Dec 10 00:00:00 EST 2014},
month = {Wed Dec 10 00:00:00 EST 2014}
}
Web of Science