HONE: Higher-Order Network Embeddings
This addresses the need for more expressive network representations in graph analysis, though it appears incremental as it builds on existing embedding methods with a flexible framework.
The paper tackled the problem of learning network embeddings from graph data by introducing a framework based on network motifs to capture higher-order structures, achieving a mean relative gain in AUC of 19% (up to 75%) over methods that cannot capture such structures.
This paper describes a general framework for learning Higher-Order Network Embeddings (HONE) from graph data based on network motifs. The HONE framework is highly expressive and flexible with many interchangeable components. The experimental results demonstrate the effectiveness of learning higher-order network representations. In all cases, HONE outperforms recent embedding methods that are unable to capture higher-order structures with a mean relative gain in AUC of $19\%$ (and up to $75\%$ gain) across a wide variety of networks and embedding methods.