no code implementations • 21 Feb 2024 • Qiang Huang, Yanhao Wang, Yiqun Sun, Anthony K. H. Tung
To bridge this gap, we revisit and refine the diversity-aware $k$MIPS (D$k$MIPS) problem by incorporating two well-known diversity objectives -- minimizing the average and maximum pairwise item similarities within the results -- into the original relevance objective.