TY - GEN
T1 - Multi-modal adversarial autoencoders for recommendations of citations and subject labels
AU - Galke, Lukas
AU - Mai, Florian
AU - Vagliano, Iacopo
AU - Scherp, Ansgar
N1 - Publisher Copyright: © 2018 Association for Computing Machinery.
PY - 2018/7/3
Y1 - 2018/7/3
N2 - We present multi-modal adversarial autoencoders for recommendation and evaluate them on two different tasks: Citation recommendation and subject label recommendation. We analyze the effects of adversarial regularization, sparsity, and different input modalities. By conducting 408 experiments, we show that adversarial regularization consistently improves the performance of autoencoders for recommendation. We demonstrate, however, that the two tasks differ in the semantics of item co-occurrence in the sense that item co-occurrence resembles relatedness in case of citations, yet implies diversity in case of subject labels. Our results reveal that supplying the partial item set as input is only helpful, when item co-occurrence resembles relatedness. When facing a new recommendation task it is therefore crucial to consider the semantics of item co-occurrence for the choice of an appropriate model.
AB - We present multi-modal adversarial autoencoders for recommendation and evaluate them on two different tasks: Citation recommendation and subject label recommendation. We analyze the effects of adversarial regularization, sparsity, and different input modalities. By conducting 408 experiments, we show that adversarial regularization consistently improves the performance of autoencoders for recommendation. We demonstrate, however, that the two tasks differ in the semantics of item co-occurrence in the sense that item co-occurrence resembles relatedness in case of citations, yet implies diversity in case of subject labels. Our results reveal that supplying the partial item set as input is only helpful, when item co-occurrence resembles relatedness. When facing a new recommendation task it is therefore crucial to consider the semantics of item co-occurrence for the choice of an appropriate model.
KW - Adversarial autoencoders
KW - Multi-modal
KW - Neural networks
KW - Recommender systems
KW - Sparsity
UR - http://www.scopus.com/inward/record.url?scp=85051724601&partnerID=8YFLogxK
U2 - https://doi.org/10.1145/3209219.3209236
DO - https://doi.org/10.1145/3209219.3209236
M3 - Conference contribution
T3 - UMAP 2018 - Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization
SP - 197
EP - 205
BT - UMAP 2018 - Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization
PB - Association for Computing Machinery, Inc
T2 - 26th ACM International Conference on User Modeling, Adaptation and Personalization, UMAP 2018
Y2 - 8 July 2018 through 11 July 2018
ER -