
<html>


<head>


<meta http-equiv="Content-Type" content="text/html; charset=utf-8">


</head>


<body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">


<div style="margin: 0px; font-stretch: normal; line-height: normal; font-family: "Helvetica Neue";" class="">


<div style="margin: 0px; font-stretch: normal; line-height: normal;" class=""><b class="">Keywords: </b>graph neural networks, commonsense reasoning, learning & reasoning, ontologies, rule based methods</div>


<div style="margin: 0px; font-stretch: normal; line-height: normal;" class=""><b class="">Deadline</b>: 26th August 2021</div>


<div style="margin: 0px; font-stretch: normal; line-height: normal;" class=""><b class="">Location</b>: Cardiff University, UK</div>


<div style="margin: 0px; font-stretch: normal; line-height: normal;" class=""><b class="">More details</b>:


<a href="https://www.jobs.ac.uk/job/CIF388/research-associate" class="">https://www.jobs.ac.uk/job/CIF388/research-associate</a></div>


</div>


<div style="margin: 0px; font-stretch: normal; line-height: normal; font-family: "Helvetica Neue";" class="">


<br class="">


</div>


<div style="margin: 0px; font-stretch: normal; line-height: normal; font-family: "Helvetica Neue";" class="">


We offer a three-year postdoctoral position at Cardiff University to work on a project on “Plausible Reasoning with Ontologies using Graph Neural Networks” funded by the Leverhulme Trust. The aim of this project is to study how the complementary strengths of


 graph neural networks and rule based methods can be combined. To this end, we will use the latent representations of GNNs to allow for a kind of commonsense reasoning with symbolic rules, allowing us to draw plausible conclusions which go beyond what can be


 logically deduced.</div>


<div class=""><br class="">


</div>


</body>


</html>