{"id":38969,"date":"2026-08-21T15:27:30","date_gmt":"2026-08-21T15:27:30","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/explainable-artificial-intelligence-reveals-divergent-learning-in-pharmacophore-based-hierarchical-pooling-graph-neural-networks\/"},"modified":"2026-09-17T11:17:22","modified_gmt":"2026-09-17T11:17:22","slug":"explainable-artificial-intelligence-reveals-divergent-learning-in-pharmacophore-based-hierarchical-pooling-graph-neural-networks","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/explainable-artificial-intelligence-reveals-divergent-learning-in-pharmacophore-based-hierarchical-pooling-graph-neural-networks\/","title":{"rendered":"Explainable artificial intelligence reveals divergent learning in pharmacophore-based hierarchical pooling graph neural networks"},"content":{"rendered":"<p>Hierarchical pooling is a promising mechanism to enhance graph neural networks ({GNNs}) by enabling multi-scale representation learning. Rationalization of hierarchical {GNN} predictions remains an underexplored area. In this work, we investigate the impact of hierarchical pooling on {GNNs} for molecular property prediction. We designed architectural variants integrating pharmacophore features with pooling {GNNs} at different levels. {GNN} models with pharmacophore-based graph reduction or hierarchical pooling achieved comparable compound classification performance. Explainable artificial intelligence ({XAI}) methods were applied to compare feature importance and substructure attribution for the different model architectures. Qualitative and quantitative analyses of the resulting explanations demonstrated that the {GNN} variants had different internal learning characteristics. {GNN} models based on reduced graphs matched the prediction accuracy of models based on complete graph representations following different variant-dependent learning strategies.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Hierarchical pooling is a promising mechanism to enhance graph neural networks ({GNNs}) by enabling multi-scale representation learning. Rationalization of hierarchical {GNN} predictions remains an underexplored area. In this work, we investigate the impact of hierarchical pooling on {GNNs} for molecular property prediction. We designed architectural variants integrating pharmacophore features with pooling {GNNs} at different levels. {GNN} models with pharmacophore-based graph reduction or hierarchical pooling achieved comparable compound classification performance. Explainable [&hellip;]<\/p>\n","protected":false},"author":14,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[30],"class_list":["post-38969","publication","type-publication","status-publish","hentry","publication-type-article"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/38969","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/14"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/38969\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=38969"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=38969"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}