HONEM: Learning Embedding for Higher Order Networks
This work addresses the challenge of accurately representing network phenomena for researchers and practitioners in network analysis, offering a novel method for handling higher-order dependencies, though it is incremental as it builds on existing embedding techniques.
The paper tackles the problem of representation learning on networks by addressing the limitation of existing methods that only capture pairwise interactions, proposing HONEM to incorporate non-Markovian higher-order dependencies, resulting in outperformance in node classification, network reconstruction, link prediction, and visualization tasks.
Representation learning on networks offers a powerful alternative to the oft painstaking process of manual feature engineering, and as a result, has enjoyed considerable success in recent years. However, all the existing representation learning methods are based on the first-order network (FON), that is, the network that only captures the pairwise interactions between the nodes. As a result, these methods may fail to incorporate non-Markovian higher-order dependencies in the network. Thus, the embeddings that are generated may not accurately represent of the underlying phenomena in a network, resulting in inferior performance in different inductive or transductive learning tasks. To address this challenge, this paper presents HONEM, a higher-order network embedding method that captures the non-Markovian higher-order dependencies in a network. HONEM is specifically designed for the higher-order network structure (HON) and outperforms other state-of-the-art methods in node classification, network re-construction, link prediction, and visualization for networks that contain non-Markovian higher-order dependencies.