Deep node ranking for neuro‐symbolic structural node embedding and classification

Abstract

Network node embedding is an active research subfield of complex network analysis. This paper contributes a novel approach to learning network node embeddings and direct node classification using a node ranking scheme, coupled with an autoencoder-based neural network architecture. The main advantages of the proposed Deep Node Ranking (DNR) algorithm are competitive or better classification performance, significantly higher learning speed and lower space requirements when compared to state-of-the-art approaches on 15 real-life structural node classification benchmarks. It also enables exploration of the relationship between symbolic and the derived sub-symbolic node representations, offering insights into the learned node space structure. To avoid the space complexity bottleneck in a direct node classification setting, DNR, if needed, computes stationary distributions of personalized random walks from given nodes in mini-batches, scaling seamlessly to larger networks. The scaling laws associated with DNR were also investigated by considering 1,488 synthetic Erdős-Rényi networks, demonstrating its scalability to tens of millions of links.

Propositionalization and Embeddings: Two Sides of the Same Coin

“…The issue is that different embedding methods have so far only been used in isolation. We already address this challenge in the current work of the authors, where we combine complementary embedding methods from different classes: in particular, to use network traversal methods to produce initial embeddings that are then refined using a deep neural network [78]. We can observe that the relevance of individual hyperparameters varies from data set to data set.…”