“…Graph embedding methods (in short, embedding methods), also known as feature representation learning methods, exploit the graph structure to represent each node in the graph as a low-dimensional vector in which neighborhood similarity, semantic information, and community structure among nodes in the graph are captured [22][23][24][25]. The obtained vector representations can be utilized by a wide range of tasks such as link prediction [22,24,[26][27][28], node classification [22,23,[25][26][27][28][29][30], recommendations [27], word analogy detection [25], and document classification [25]. Embedding methods, which are effective for extracting features from graph structured data, have broadly attracted significant attention in the literature and different embedding methods such as DeepWalk [23], Line [25], node2vec [26], graph-GAN [27], NetMF [29], ATP [24], BoostNE [30], DWNS [22], and NERD [28] have been proposed for homogeneous graphs.…”