Graph Structural Aggregation for Explainable Learning
Graph neural networks have proven to be very efficient to solve several tasks in graphs such as node classification or link prediction. These algorithms that operate by propagating information from vertices to their neighbors allow one to build node embeddings that contain local information. In order to use graph neural networks for graph classification, node embeddings must be aggregated to obtain a graph representation able to discriminate among different graphs (of possibly various sizes). Moreover, in analogy to neural networks for image classification, there is a need for explainability regarding the features that are selected in the graph classification process. To this end, we introduce StructAgg, a simple yet effective aggregation process based on the identification of structural roles for nodes in graphs that we use to create an end-to-end model. Through extensive experiments we show that this architecture can compete with state-of-the-art methods. We show how this aggregation step allows us to cluster together nodes that have comparable structural roles and how these roles provide explainability to this neural network model.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationGraph Classificationimage-classificationImage ClassificationLink PredictionNode ClassificationSimilar Papers 제목 키워드 기반
Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning
Graph Neural Networks (GNNs) have become essential in high-stakes domains such as drug discovery, yet their black-box nature remains a significant barrier to trustworthiness. While self-explainable GNNs attempt to bridge…
Graph LearningDrug DiscoveryStructural Graph Neural Networks with Anatomical Priors for Explainable Chest X-ray Diagnosis
We present a structural graph reasoning framework that incorporates explicit anatomical priors for explainable vision-based diagnosis. Convolutional feature maps are reinterpreted as patch-level graphs, where nodes encod…
Relational ReasoningUnderstanding Alzheimer disease’s structural connectivity through explainable AI
In the following work, we use a modified version of deep BrainNet convolutional neural network (CNN) trained on the diffusion weighted MRI (DW-MRI) tractography connectomes of patients with Alzheimer’s Disease (AD) and M…
Diffusion MRIGraLSP: Graph Neural Networks with Local Structural Patterns
It is not until recently that graph neural networks (GNNs) are adopted to perform graph representation learning, among which, those based on the aggregation of features within the neighborhood of a node achieved great su…
Graph Representation LearningRepresentation LearningMitigating Molecular Aggregation in Drug Discovery with Predictive Insights from Explainable AI
Herein, we present the application of MEGAN, our explainable AI (xAI) model, for the identification of small colloidally aggregating molecules (SCAMs). This work offers solutions to the long-standing problem of false pos…
Drug Discovery