{"id":1260,"date":"2023-08-07T13:34:56","date_gmt":"2023-08-07T13:34:56","guid":{"rendered":"https:\/\/prg.inf.unibe.ch\/?page_id=1260"},"modified":"2024-11-13T13:47:06","modified_gmt":"2024-11-13T13:47:06","slug":"thesis-learning-graph-edit-distance-via-reinforcement-learning","status":"publish","type":"page","link":"https:\/\/prg.inf.unibe.ch\/index.php\/education\/thesis-learning-graph-edit-distance-via-reinforcement-learning\/","title":{"rendered":"thesis-Learning-Graph-Edit-Distance-via-Reinforcement-Learning"},"content":{"rendered":"\n<div style=\"height:150px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<section class=\"wp-block-uagb-columns uagb-columns__wrap uagb-columns__background-none uagb-columns__stack-mobile uagb-columns__valign- uagb-columns__gap-10 align uagb-block-73137d87 uagb-columns__columns-1 uagb-columns__max_width-theme\"><div class=\"uagb-columns__overlay\"><\/div><div class=\"uagb-columns__inner-wrap uagb-columns__columns-1\">\n<div class=\"wp-block-uagb-column uagb-column__wrap uagb-column__background-undefined uagb-block-1e737c18\"><div class=\"uagb-column__overlay\"><\/div>\n<h1 class=\"wp-block-heading\">Learning Graph Edit Distance via Reinforcement Learning<\/h1>\n\n\n\n<p><strong>Supervised by:<\/strong> <a href=\"mailto:anthony.gillioz@unibe.ch\">Anthony Gillioz<\/a><\/p>\n\n\n\n<p>If you are interested in this topic or have further questions, do not hesitate to contact me.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Context\/Background\/Current State<\/h2>\n\n\n\n<p>Graph Edit Distance (GED) is a popular technique used to match and compare pairs of graphs. Basically, GED finds the minimal set of\u00a0edit operations that transform a source graph\u00a0<code>g<sub>s<\/sub><\/code> into a target graph<code> g<sub>t<\/sub><\/code>. GED turns out to be very flexible and intuitive.\u00a0However, GED&#8217;s\u00a0drawback lies in its computational complexity, making it impractical for\u00a0graphs with a substantial number of nodes (for graphs with several thousands of nodes, for instance, GED is\u00a0definitely unfeasible).<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Goal(s)<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>The current research project aims to use\u00a0reinforcement learning to learn edit operations, with the hope of\u00a0speeding up GED computation at inference time.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Approach<\/h2>\n\n\n\n<p>TBD with the supervisor.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Required Skills<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Good programming skills, particularly working with different frameworks.\u00a0<\/li>\n\n\n\n<li>Basic knowledge of reinforcement learning\u00a0and graphs.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Remarks<\/h2>\n\n\n\n<p>Achieving a good and practical solution with these models is a complex task,\u00a0especially when dealing with Out-of-Distribution Data\u00a0(that is data that were not in the training set).<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Further Reading<\/h2>\n\n\n\n<p><\/p>\n<\/div>\n<\/div><\/section>\n","protected":false},"excerpt":{"rendered":"<p>Learning Graph Edit Distance via Reinforcement Learning Supervised by: Anthony Gillioz If you are interested in this topic or have further questions, do not hesitate to contact me. Context\/Background\/Current State Graph Edit Distance (GED) is a popular technique used to match and compare pairs of graphs. Basically, GED finds the minimal set of\u00a0edit operations that &hellip;<\/p>\n<p class=\"read-more\"> <a class=\"\" href=\"https:\/\/prg.inf.unibe.ch\/index.php\/education\/thesis-learning-graph-edit-distance-via-reinforcement-learning\/\"> <span class=\"screen-reader-text\">thesis-Learning-Graph-Edit-Distance-via-Reinforcement-Learning<\/span> Read More &raquo;<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":731,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_uag_custom_page_level_css":"","site-sidebar-layout":"no-sidebar","site-content-layout":"plain-container","ast-global-header-display":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"disabled","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"enabled","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","footnotes":""},"class_list":["post-1260","page","type-page","status-publish","hentry"],"uagb_featured_image_src":{"full":false,"thumbnail":false,"medium":false,"medium_large":false,"large":false,"1536x1536":false,"2048x2048":false},"uagb_author_info":{"display_name":"prg-admin","author_link":"https:\/\/prg.inf.unibe.ch\/index.php\/author\/prg-admin\/"},"uagb_comment_info":0,"uagb_excerpt":"Learning Graph Edit Distance via Reinforcement Learning Supervised by: Anthony Gillioz If you are interested in this topic or have further questions, do not hesitate to contact me. Context\/Background\/Current State Graph Edit Distance (GED) is a popular technique used to match and compare pairs of graphs. Basically, GED finds the minimal set of\u00a0edit operations that&hellip;","_links":{"self":[{"href":"https:\/\/prg.inf.unibe.ch\/index.php\/wp-json\/wp\/v2\/pages\/1260","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prg.inf.unibe.ch\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/prg.inf.unibe.ch\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/prg.inf.unibe.ch\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prg.inf.unibe.ch\/index.php\/wp-json\/wp\/v2\/comments?post=1260"}],"version-history":[{"count":3,"href":"https:\/\/prg.inf.unibe.ch\/index.php\/wp-json\/wp\/v2\/pages\/1260\/revisions"}],"predecessor-version":[{"id":1428,"href":"https:\/\/prg.inf.unibe.ch\/index.php\/wp-json\/wp\/v2\/pages\/1260\/revisions\/1428"}],"up":[{"embeddable":true,"href":"https:\/\/prg.inf.unibe.ch\/index.php\/wp-json\/wp\/v2\/pages\/731"}],"wp:attachment":[{"href":"https:\/\/prg.inf.unibe.ch\/index.php\/wp-json\/wp\/v2\/media?parent=1260"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}