Advancing Edge Classification through High-Dimensional Causal Modeling of Node-Edge Interplay
This work addresses the under-explored edge classification task by providing a causal modeling approach that improves performance, but the novelty is incremental as it applies existing causal principles to a new graph task.
The paper introduces CECF, the first causal inference framework for edge classification, which models high-dimensional edge features while mitigating node feature influence. Experiments show it achieves superior performance and can be used as a plug-and-play enhancement for existing methods.
Edge classification, a crucial task for graph applications, remains relatively under-explored compared to link prediction. Current methods often overlook the potential causal influences of node features on edge features, leading to a loss of relevant prior information. In this work, we present an empirical exploration using the Causal Edge Classification Framework (CECF). Unlike conventional causal inference methods, CECF is the first framework to apply causal inference principles to the edge classification task and to explore modeling edge features as a high-dimensional treatment within a causal framework. Based on the node embedding of Graph Neural Network (GNN), CECF seeks to learn a balanced representation of high-dimensional edge features by mitigating the potential influence of node features. Then, a cross-attention network captures the complex dependencies between node and edge features for final edge classification.Extensive experiments demonstrate that CECF not only achieves superior performance but also serves as a flexible, plug-and-play enhancement for existing methods.We also provide empirical analyses, offering insights into when and how this high-dimensional causal modeling framework works for the edge classification.