Causal Temporal Graph Convolutional Neural Networks (CTGCN)
This work addresses scalability and explainability issues in graph neural networks for applications with limited domain knowledge, representing an incremental advancement.
The paper tackles the scalability and domain knowledge limitations of graph-based applications by proposing a Causal Temporal Graph Convolutional Neural Network (CTGCN), which improves prediction performance by up to 40% over typical TGCN approaches on large-scale datasets.
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.