Temporal Graph Network Embedding with Causal Anonymous Walks Representations

TL;DR

This paper introduces a novel temporal graph embedding method using Causal Anonymous Walks within a Temporal Graph Network framework, providing a comprehensive benchmark and demonstrating superior performance in real-world credit scoring tasks.

Contribution

The paper presents a new approach for dynamic network embedding using Causal Anonymous Walks and offers the first extensive benchmark for temporal graph representation learning.

Findings

Outperforms state-of-the-art models in node classification and link prediction.

Provides a comprehensive evaluation framework for temporal network embeddings.

Demonstrates real-world applicability in credit scoring for a European bank.

Abstract

Many tasks in graph machine learning, such as link prediction and node classification, are typically solved by using representation learning, in which each node or edge in the network is encoded via an embedding. Though there exists a lot of network embeddings for static graphs, the task becomes much more complicated when the dynamic (i.e. temporal) network is analyzed. In this paper, we propose a novel approach for dynamic network representation learning based on Temporal Graph Network by using a highly custom message generating function by extracting Causal Anonymous Walks. For evaluation, we provide a benchmark pipeline for the evaluation of temporal network embeddings. This work provides the first comprehensive comparison framework for temporal network representation learning in every available setting for graph machine learning problems involving node classification and link prediction. The proposed model outperforms state-of-the-art baseline models. The work also justifies the difference between them based on evaluation in various transductive/inductive edge/node classification tasks. In addition, we show the applicability and superior performance of our model in the real-world downstream graph machine learning task provided by one of the top European banks, involving credit scoring based on transaction data.