A Parameterized Neural Network is a type of neural network in which the model’s architecture includes parameters that are learned during the training process. These parameters determine the strength and nature of connections between neurons in the network, allowing the model to adapt and make predictions based on input data. Parameterized neural networks are versatile and can be applied to a wide range of tasks, from image recognition and natural language processing to regression and reinforcement learning. The success of these networks lies in their ability to automatically learn and represent complex patterns in data through the adjustment of parameters during training.

Posts

Parameterized Explainer for Graph Neural Network

Parameterized Explainer for Graph Neural Network Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging open problem. The leading method independently addresses the local explanations (i.e., important subgraph structure and node features) to interpret why a GNN model makes the prediction for a single instance, e.g. a node or a graph. As a result, the explanation generated is painstakingly customized for each instance. The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to the lack of generalizability and hindering it from being used in the inductive setting. Besides, as it is designed for explaining a single instance, it is challenging to explain a set of instances naturally (e.g., graphs of a given class). In this study, we address these key challenges and propose PGExplainer, a parameterized explainer for GNNs. PGExplainer adopts a deep neural network to parameterize the generation process of explanations, which enables PGExplainer a natural approach to explaining multiple instances collectively. Compared to the existing work, PGExplainer has better generalization ability and can be utilized in an inductive setting easily. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24.7% relative improvement in AUC on explaining graph classification over the leading baseline.