GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks
This addresses the interpretability challenge for users of GNNs in real-life scenarios, though it is incremental as it builds on existing model-level explanation methods.
The paper tackles the problem of interpreting graph neural networks (GNNs) as black boxes by proposing GIN-Graph, a generative model that produces reliable and high-quality explanation graphs, with experimental results showing high stability and reliability across various datasets.
One significant challenge of exploiting Graph neural networks (GNNs) in real-life scenarios is that they are always treated as black boxes, therefore leading to the requirement of interpretability. To address this, model-level interpretation methods have been developed to explain what patterns maximize probability of predicting to a certain class. However, existing model-level interpretation methods pose several limitations such as generating invalid explanation graphs and lacking reliability. In this paper, we propose a new Generative Interpretation Network for Model-Level Explanation of Graph Neural Networks (GIN-Graph), to generate reliable and high-quality model-level explanation graphs. The implicit and likelihood-free generative adversarial networks are exploited to construct the explanation graphs which are similar to original graphs, meanwhile maximizing the prediction probability for a certain class by adopting a novel objective function for generator with dynamic loss weight scheme. Experimental results indicate that GIN-Graph can be applied to interpret GNNs trained on a variety of graph datasets and generate high-quality explanation graphs with high stability and reliability.