Causal Temporal Graph Convolutional Neural Networks (CTGCN)

TL;DR

The paper introduces CTGCN, a scalable, explainable causal discovery-based neural network for large-scale graph data, significantly improving prediction accuracy without domain knowledge.

Contribution

It presents a novel CTGCN architecture that integrates causal discovery with temporal graph convolutional networks, enhancing scalability and interpretability.

Findings

Achieves up to 40% better prediction accuracy over traditional TGCN.

Demonstrates scalability on large datasets.

Operates without requiring domain-specific knowledge.

Abstract

Many large-scale applications can be elegantly represented using graph structures. Their scalability, however, is often limited by the domain knowledge required to apply them. To address this problem, we propose a novel Causal Temporal Graph Convolutional Neural Network (CTGCN). Our CTGCN architecture is based on a causal discovery mechanism, and is capable of discovering the underlying causal processes. The major advantages of our approach stem from its ability to overcome computational scalability problems with a divide and conquer technique, and from the greater explainability of predictions made using a causal model. We evaluate the scalability of our CTGCN on two datasets to demonstrate that our method is applicable to large scale problems, and show that the integration of causality into the TGCN architecture improves prediction performance up to 40% over typical TGCN approach. Our results are obtained without requiring additional domain knowledge, making our approach adaptable to various domains, specifically when little contextual knowledge is available.