Advancing Edge Classification through High-Dimensional Causal Modeling of Node-Edge Interplay

TL;DR

This paper introduces a novel causal inference framework for edge classification in graphs, leveraging high-dimensional modeling of node-edge interactions to improve performance and interpretability.

Contribution

It is the first to apply causal inference principles to edge classification, modeling edge features as high-dimensional treatments within a GNN-based framework.

Findings

CECF achieves superior classification performance.

The framework effectively mitigates node feature influence.

Empirical analyses reveal when high-dimensional causal modeling is most effective.

Abstract

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.