“…We compare MCLET with three types of baselines. (i) embedding-based models: ETE (Moon et al, 2017), ConnectE (Zhao et al,Datasets FB15kET YAGO43kET Metrics MRR Hits@1 Hits@3 Hits@10 MRR Hits@1 Hits@3 Hits@10 Embedding-based methods ETE (Moon et al, 2020) and CORE (Ge et al, 2021); (ii) GNNbased models: HMGCN (Jin et al, 2019), At-tEt (Zhuo et al, 2022), ConnectE-MRGAT , RACE2T (Zou et al, 2022a), CompGCN (Vashishth et al, 2020) RGCN (Pan et al, 2021), CET (Pan et al, 2021), and MiNer (Jin et al, 2022); (iii) transformer-based models: CoKE (Wang et al, 2019), HittER (Chen et al, 2021) and TET (Hu et al, 2022a).…”