1 Hit in 1.8 sec

Hierarchical User Intent Graph Network forMultimedia Recommendation [article]

Wei Yinwei, Wang Xiang, He Xiangnan, Nie Liqiang, Rui Yong, Chua Tat-Seng
2021 arXiv   pre-print
Towards this end, we develop a novel framework, Hierarchical User Intent Graph Network, which exhibits user intents in a hierarchical graph structure, from the fine-grained to coarse-grained intents.  ...  In this work, we aim to learn multi-level user intents from the co-interacted patterns of items, so as to obtain high-quality representations of users and items and further enhance the recommendation performance  ...  Upon such a cointeracted graph, we then develop a Hierarchical User Intent Graph Network (HUIGN), which learns the multilevel user intents' representations as well as the hierarchical structure.  ... 
arXiv:2110.14925v1 fatcat:wyhcq6n6yzap7iodibgoo4hvgq