TY - JOUR
T1 - FuseRec
T2 - fusing user and item homophily modeling with temporal recommender systems
AU - Narang, Kanika
AU - Song, Yitong
AU - Schwing, Alexander Gerhard
AU - Sundaram, Hari
N1 - Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer Science+Business Media LLC, part of Springer Nature.
PY - 2021/5
Y1 - 2021/5
N2 - Recommender systems can benefit from a plethora of signals influencing user behavior such as her past interactions, her social connections, as well as the similarity between different items. However, existing methods are challenged when taking all this data into account and often do not exploit all available information. This is primarily due to the fact that it is non-trivial to combine the various information as they mutually influence each other. To address this shortcoming, here, we propose a ‘Fusion Recommender’ (FuseRec), which models each of these factors separately and later combines them in an interpretable manner. We find this general framework to yield compelling results on all three investigated datasets, Epinions, Ciao, and CiaoDVD, outperforming the state-of-the-art by more than 14% for Ciao and Epinions. In addition, we provide a detailed ablation study, showing that our combined model achieves accurate results, often better than any of its components individually. Our model also provides insights on the importance of each of the factors in different datasets.
AB - Recommender systems can benefit from a plethora of signals influencing user behavior such as her past interactions, her social connections, as well as the similarity between different items. However, existing methods are challenged when taking all this data into account and often do not exploit all available information. This is primarily due to the fact that it is non-trivial to combine the various information as they mutually influence each other. To address this shortcoming, here, we propose a ‘Fusion Recommender’ (FuseRec), which models each of these factors separately and later combines them in an interpretable manner. We find this general framework to yield compelling results on all three investigated datasets, Epinions, Ciao, and CiaoDVD, outperforming the state-of-the-art by more than 14% for Ciao and Epinions. In addition, we provide a detailed ablation study, showing that our combined model achieves accurate results, often better than any of its components individually. Our model also provides insights on the importance of each of the factors in different datasets.
KW - Attention-based graph networks
KW - Item similarity modeling
KW - Social recommendation
KW - Temporal recommender systems
UR - http://www.scopus.com/inward/record.url?scp=85101456382&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85101456382&partnerID=8YFLogxK
U2 - 10.1007/s10618-021-00738-8
DO - 10.1007/s10618-021-00738-8
M3 - Article
AN - SCOPUS:85101456382
SN - 1384-5810
VL - 35
SP - 837
EP - 862
JO - Data Mining and Knowledge Discovery
JF - Data Mining and Knowledge Discovery
IS - 3
ER -