Transcription of Adversarial Feature Translation for Multi-domain ...
{{id}} {{{paragraph}}}
Example: air traffic controller
Adversarial Feature Translation for Multi-domain ...
Adversarial Feature Translation for Multi-domainRecommendationXiaobo Hao WeChat, TencentBeijing, Liu WeChat, TencentBeijing, Xie WeChat, TencentBeijing, GeWeChat, TencentBeijing, TangWeChat, TencentBeijing, ZhangWeChat, TencentBeijing, LinWeChat, TencentBeijing, super platforms such as Google and WeChat usuallyhave different recommendation scenarios to provide heterogeneousitems for users diverse demands. Multi-domain recommendation(MDR) is proposed to improve all recommendation domains simul-taneously, where the key point is to capture informative domain-specific features from all domains.
There are some works that focus on user’s multiple behaviors (e.g., click, unclick, purchase). ATRank [32] models multiple types of behaviors via self-attention. MBGCN [10] brings in graph convolu-tional networks. These models can be used in MDR with the behav-iors replaced by the multi-domain behaviors. Multi-task learning is
Loading..
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: