⚫ Maximal Marginal Relevance (MMR)[5] ⚫ Determinantal Point Process (DPP)[6] ⚫ DGRec[34] ⚫評価対象 ⚫ 推薦結果全体 ⚫ 効果的なアイテム群(:= 推薦結果とテストデータの積集合) 予備調査|効果的な推薦かを区別できていない例(1/2) [43] Joint optimization of tree-based index and deep model for recommender systems (NeurIPS'19) [44] Learning tree-based deep model for recommender systems (KDD'18) [5] The use of MMR, diversity-based reranking for reordering documents and producing summaries (SIGIR'98) [6] Fast greedy map inference for determinantal point process to improve recommendation diversity (NeurIPS'18) [34] DGRec: Graph Neural Network for Recommendation with Diversified Embedding Generation (WSDM'23)