一作SIGIR 2026Oral· Information Retrieval (Full)
Inferring Targets from Calibrated Hesitations via Mutual Information Maximization in Multi-Behavior Recommendation
Cheng Li · Yong Xu · Suhua Tang · Xin He · Jianfeng Sun · Jinde Cao
摘要
Multi-behavior recommendation enriches user preference modeling by incorporating diverse auxiliary interactions. However, most existing methods simply treat interactions without target behaviors as absolute negative feedback. This strategy ignores an important intermediate state known as user hes...