“…Furthermore, attentively aggregating the hierarchical structural features enhances the node expressivity, thereby overcoming the over-smoothing problem. While some approaches have also used graphlet information (Almulhim et al, 2019) however, they treat them as node attributes, as opposed to our method, which uses the graphlets as structural features to determine their correlation across the networks. Several other existing methods that have also used higher-order structures (Zhang et al, 2019;Qiu et al, 2021;Xia et al, 2021), to generate the node representations neither make any attempt to learn the embeddings jointly nor consider capturing the structural variations across the network.…”