Unifying Homophily and Heterophily Network Transformation via Motifs
This work addresses the limitation of existing network embedding methods that only consider either homophily or heterophily, providing a more comprehensive approach for network analysis researchers.
This paper proposes a framework called Homophily and Heterophily Preserving Network Transformation (H2NT) to unify homophily and heterophily in higher-order proximity for network embedding. It achieves this by transforming networks using motif representations and can be integrated with existing network embedding methods. When integrated with DeepWalk, H2NT improves motif prediction precision by 24% and reduces computational time by 46%.
Higher-order proximity (HOP) is fundamental for most network embedding methods due to its significant effects on the quality of node embedding and performance on downstream network analysis tasks. Most existing HOP definitions are based on either homophily to place close and highly interconnected nodes tightly in embedding space or heterophily to place distant but structurally similar nodes together after embedding. In real-world networks, both can co-exist, and thus considering only one could limit the prediction performance and interpretability. However, there is no general and universal solution that takes both into consideration. In this paper, we propose such a simple yet powerful framework called homophily and heterophliy preserving network transformation (H2NT) to capture HOP that flexibly unifies homophily and heterophily. Specifically, H2NT utilises motif representations to transform a network into a new network with a hybrid assumption via micro-level and macro-level walk paths. H2NT can be used as an enhancer to be integrated with any existing network embedding methods without requiring any changes to latter methods. Because H2NT can sparsify networks with motif structures, it can also improve the computational efficiency of existing network embedding methods when integrated. We conduct experiments on node classification, structural role classification and motif prediction to show the superior prediction performance and computational efficiency over state-of-the-art methods. In particular, DeepWalk-based H2 NT achieves 24% improvement in terms of precision on motif prediction, while reducing 46% computational time compared to the original DeepWalk.