Time-varying Graph Representation Learning via Higher-Order Skip-Gram with Negative Sampling

Simone Piaggesi, André Panisson

Keywords: representation learning, node embeddings, temporal graphs, tensor factorization, disease spreading

Abstract: Representation learning models for graphs are a successful family of techniques that project nodes into feature spaces that can be exploited by other machine learning algorithms. Since many real-world networks are inherently dynamic, with interactions among nodes changing over time, these techniques can be defined both for static and for time-varying graphs. Here, we show how the skip-gram embedding approach can be used to perform implicit tensor factorization on different tensor representations of time-varying graphs. We show that higher-order skip-gram with negative sampling (HOSGNS) is able to disentangle the role of nodes and time, with a small fraction of the number of parameters needed by other approaches. We empirically evaluate our approach using time-resolved face-to-face proximity data, showing that the learned representations outperform state-of-the-art methods when used to solve downstream tasks such as network reconstruction. Good performance on predicting the outcome of dynamical processes such as disease spreading shows the potential of this new method to estimate contagion risk, providing early risk awareness based on contact tracing data.

One-sentence Summary: Unsupervised representation learning algorithm for temporal graphs which disentagles structural and temporal features into different embedding matrices.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2006.14330/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=Sz57_sE5Or