TY - GEN
T1 - Temporal recommendation on graphs via long- and short-term preference fusion
AU - Xiang, Liang
AU - Yuan, Quan
AU - Zhao, Shiwan
AU - CHEN, Li
AU - Zhang, Xiatian
AU - Yang, Qing
AU - Sun, Jimeng
N1 - Copyright:
Copyright 2010 Elsevier B.V., All rights reserved.
PY - 2010
Y1 - 2010
N2 - Accurately capturing user preferences over time is a great practical challenge in recommender systems. Simple correlation over time is typically not meaningful, since users change their preferences due to different external events. User behavior can often be determined by individual's long-term and short-term preferences. How to represent users' long-term and short-term preferences? How to leverage them for temporal recommendation? To address these challenges, we propose Session-based Temporal Graph (STG) which simultaneously models users' long-term and short-term preferences over time. Based on the STG model framework, we propose a novel recommendation algorithm Injected Preference Fusion (IPF) and extend the personalized Random Walk for temporal recommendation. Finally, we evaluate the effectiveness of our method using two real datasets on citations and social bookmarking, in which our proposed method IPF gives 15%-34% improvement over the previous state-of-the-art.
AB - Accurately capturing user preferences over time is a great practical challenge in recommender systems. Simple correlation over time is typically not meaningful, since users change their preferences due to different external events. User behavior can often be determined by individual's long-term and short-term preferences. How to represent users' long-term and short-term preferences? How to leverage them for temporal recommendation? To address these challenges, we propose Session-based Temporal Graph (STG) which simultaneously models users' long-term and short-term preferences over time. Based on the STG model framework, we propose a novel recommendation algorithm Injected Preference Fusion (IPF) and extend the personalized Random Walk for temporal recommendation. Finally, we evaluate the effectiveness of our method using two real datasets on citations and social bookmarking, in which our proposed method IPF gives 15%-34% improvement over the previous state-of-the-art.
KW - Graph
KW - Temporal recommendation
KW - User preference
UR - http://www.scopus.com/inward/record.url?scp=77956220287&partnerID=8YFLogxK
U2 - 10.1145/1835804.1835896
DO - 10.1145/1835804.1835896
M3 - Conference proceeding
AN - SCOPUS:77956220287
SN - 9781450300551
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 723
EP - 731
BT - KDD'10 - Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data
T2 - 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD-2010
Y2 - 25 July 2010 through 28 July 2010
ER -