Causal Temporal Graph Convolutional Neural Networks (CTGCN)

2023/03/16 by Abigail Langbridge, Fearghal O’Donncha, Langbridge, Abigail +9
Computer Science · #Advanced Graph Neural Networks #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2303.09634

openalex publication_date 2023/03/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• TS-CausalNN: Learning Temporal Causal Relations from Non-linear Non-stationary Time Series Data
• Towards Causal Classification: A Comprehensive Study on Graph Neural Networks
• Exploring Causal Learning through Graph Neural Networks: An In-depth Review
• CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery
• Enhancing the Performance of Neural Networks Through Causal Discovery and Integration of Domain Knowledge