“…GAN proposes to train a pair of discriminator and generator by playing a min-max game between them and achieve better performance, which has been widely used in various fields such as computer vision [1,19], natural language processing [9,58], information retrieval [44,59], and recommender systems [50,52,58]. In the KGC field, there are some methods [4,30,39,46] employs a GAN-based framework to enhance the negative sampling [3] process. For example, KBGAN [4] utilizes reinforcement learning (RL) with GAN to learn a better sampling policy.…”