DeepAI AI Chat
Log In Sign Up

OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks

by   Wanyu Lin, et al.
The Hong Kong Polytechnic University

This paper proposes a new eXplanation framework, called OrphicX, for generating causal explanations for any graph neural networks (GNNs) based on learned latent causal factors. Specifically, we construct a distinct generative model and design an objective function that encourages the generative model to produce causal, compact, and faithful explanations. This is achieved by isolating the causal factors in the latent space of graphs by maximizing the information flow measurements. We theoretically analyze the cause-effect relationships in the proposed causal graph, identify node attributes as confounders between graphs and GNN predictions, and circumvent such confounder effect by leveraging the backdoor adjustment formula. Our framework is compatible with any GNNs, and it does not require access to the process by which the target GNN produces its predictions. In addition, it does not rely on the linear-independence assumption of the explained features, nor require prior knowledge on the graph learning tasks. We show a proof-of-concept of OrphicX on canonical classification problems on graph data. In particular, we analyze the explanatory subgraphs obtained from explanations for molecular graphs (i.e., Mutag) and quantitatively evaluate the explanation performance with frequently occurring subgraph patterns. Empirically, we show that OrphicX can effectively identify the causal semantics for generating causal explanations, significantly outperforming its alternatives.


Generative Causal Explanations for Graph Neural Networks

This paper presents Gem, a model-agnostic approach for providing interpr...

Generative causal explanations of black-box classifiers

We develop a method for generating causal post-hoc explanations of black...

Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment

Uncovering rationales behind predictions of graph neural networks (GNNs)...

On Consistency in Graph Neural Network Interpretation

Uncovering rationales behind predictions of graph neural networks (GNNs)...

Deconfounding to Explanation Evaluation in Graph Neural Networks

Explainability of graph neural networks (GNNs) aims to answer “Why the G...

Reinforced Causal Explainer for Graph Neural Networks

Explainability is crucial for probing graph neural networks (GNNs), answ...

Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure

Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by...