Inference of Sequential Patterns for Neural Message Passing in Temporal Graphs

Jan von Pichowski, Vincenzo Perri, Lisi Qarkaxhija, Ingo Scholtes

Keywords: graph neural networks, dynamic graph, higher order network, time series data, temporal network, random graph ensembles

Abstract:

The modelling of temporal patterns in dynamic graphs is an important current research issue in the development of time-aware Graph Neural Networks (GNNs).
However, whether or not a specific sequence of events in a temporal graph constitutes a temporal pattern not only depends on the frequency of its occurrence.
We must also consider whether it deviates from what is expected in a temporal graph where timestamps are randomly shuffled.
While accounting for such a random baseline is important to model temporal patterns, it has mostly been ignored by current temporal graph neural networks.
To address this issue we propose HYPA-DBGNN, a novel two-step approach that combines (i) the inference of anomalous sequential patterns in time series data on graphs based on a statistically principled null model, with (ii) a neural message passing approach that utilizes a higher-order De Bruijn graph whose edges capture overrepresented sequential patterns.
Our method leverages hypergeometric graph ensembles to identify anomalous edges within both first- and higher-order De Bruijn graphs, which encode the temporal ordering of events.
Consequently, the model introduces an inductive bias that enhances model interpretability and leads to improved performance.

Submission Type: Extended abstract (max 4 main pages).

Software: https://github.com/jvpichowski/HYPA-DBGNN

Submission Number: 97