PieClam: A Universal Graph Autoencoder Based on Overlapping Inclusive and Exclusive Communities

TL;DR

PieClam is a universal graph autoencoder that models overlapping inclusive and exclusive communities using a probabilistic approach, incorporating a learned prior, and employing a novel Lorentz inner product decoder for improved expressiveness.

Contribution

It introduces a probabilistic community affiliation model with a new Lorentz inner product decoder, extending existing methods to include disconnection-based communities and a learned prior.

Findings

Achieves competitive results in graph anomaly detection.

Proves to be a universal autoencoder capable of reconstructing any graph.

Demonstrates improved expressiveness over standard decoders.

Abstract

We propose PieClam (Prior Inclusive Exclusive Cluster Affiliation Model): a probabilistic graph model for representing any graph as overlapping generalized communities. Our method can be interpreted as a graph autoencoder: nodes are embedded into a code space by an algorithm that maximizes the log-likelihood of the decoded graph, given the input graph. PieClam is a community affiliation model that extends well-known methods like BigClam in two main manners. First, instead of the decoder being defined via pairwise interactions between the nodes in the code space, we also incorporate a learned prior on the distribution of nodes in the code space, turning our method into a graph generative model. Secondly, we generalize the notion of communities by allowing not only sets of nodes with strong connectivity, which we call inclusive communities, but also sets of nodes with strong disconnection, which we call exclusive communities. To model both types of communities, we propose a new type of decoder based the Lorentz inner product, which we prove to be much more expressive than standard decoders based on standard inner products or norm distances. By introducing a new graph similarity measure, that we call the log cut distance, we show that PieClam is a universal autoencoder, able to uniformly approximately reconstruct any graph. Our method is shown to obtain competitive performance in graph anomaly detection benchmarks.