Exact Representation of Sparse Networks with Symmetric Nonnegative Embeddings

Published: 21 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: graph, network, embeddings, arboricity, factorization, model, community, nonnegative
TL;DR: We expand on previous bounds for exact factorization of undirected graphs and extend them to our proposed model, which is more interpretable.
Abstract: Graph models based on factorization of the adjacency matrix often fail to capture network structures related to links between dissimilar nodes (heterophily). We introduce a novel graph factorization model that leverages two nonnegative vectors per node to interpretably account for links between both similar and dissimilar nodes. We prove that our model can exactly represent any graph with low *arboricity*, a property that many real-world networks satisfy; our proof also applies to related models but has much greater scope than the closest prior bound, which is based on low *max degree*. Our factorization also has compelling properties besides expressiveness: due to its symmetric structure and nonnegativity, fitting the model inherently finds node communities, and the model's link predictions can be interpreted in terms of these communities. In experiments on real-world networks, we demonstrate our factorization's effectiveness on a variety of tasks, including community detection and link prediction.
Supplementary Material: zip
Submission Number: 8921