{"id":6354,"date":"2025-08-26T07:02:35","date_gmt":"2025-08-26T07:02:35","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/08\/26\/2508-16995\/"},"modified":"2025-08-26T07:02:35","modified_gmt":"2025-08-26T07:02:35","slug":"2508-16995","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/08\/26\/2508-16995\/","title":{"rendered":"GraphPPD: Posterior Predictive Modelling for Graph-Level Inference"},"content":{"rendered":"

GraphPPD: Posterior Predictive Modelling for Graph-Level Inference
\n \t

\n
<\/BR>
\n
\n \t

\n
<\/BR><\/p>\n

arXiv:2508.16995v1 Announce Type: new
\nAbstract: Accurate modelling and quantification of predictive uncertainty is crucial in deep learning since it allows a model to make safer decisions when the data is ambiguous and facilitates the users’ understanding of the model’s confidence in its predictions. Along with the tremendously increasing research focus on emph{graph neural networks} (GNNs) in recent years, there have been numerous techniques which strive to capture the uncertainty in their predictions. However, most of these approaches are specifically designed for node or link-level tasks and cannot be directly applied to graph-level learning problems. In this paper, we propose a novel variational modelling framework for the emph{posterior predictive distribution}~(PPD) to obtain uncertainty-aware prediction in graph-level learning tasks. Based on a graph-level embedding derived from one of the existing GNNs, our framework can learn the PPD in a data-adaptive fashion. Experimental results on several benchmark datasets exhibit the effectiveness of our approach.<\/div>\n

\t

\n
<\/BR>
\n Soumyasundar Pal, Liheng Ma, Amine Natik, Yingxue Zhang, Mark Coates
\n \t

\n
<\/BR>
\nGo to original source<\/a>
\n \t

\n
<\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"

GraphPPD: Posterior Predictive Modelling for Graph-Level Inference arXiv:2508.16995v1 Announce Type: new Abstract: Accurate modelling and quantification of predictive uncertainty is crucial in deep learning since it allows a model to make safer decisions when the data is ambiguous and facilitates the users’ understanding of the model’s confidence in its predictions. Along with the tremendously increasing […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,113,112],"tags":[339,161,716],"class_list":["post-6354","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-stat-ml","tag-graph","tag-level","tag-predictive"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/6354"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=6354"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/6354\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=6354"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=6354"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=6354"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}