{"id":1021,"date":"2021-04-12T12:32:58","date_gmt":"2021-04-12T11:32:58","guid":{"rendered":"http:\/\/pages.di.unipi.it\/bacciu\/?p=1021"},"modified":"2021-04-12T12:34:31","modified_gmt":"2021-04-12T11:34:31","slug":"ijcnn-2021-papers","status":"publish","type":"post","link":"https:\/\/pages.di.unipi.it\/bacciu\/2021\/04\/12\/ijcnn-2021-papers\/","title":{"rendered":"IJCNN 2021 papers"},"content":{"rendered":"\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-large\"><img decoding=\"async\" src=\"https:\/\/pages.di.unipi.it\/bacciu\/wp-content\/uploads\/sites\/12\/2021\/04\/injcnn.png\" alt=\"\" class=\"wp-image-1022\" \/><\/figure><\/div>\n\n\n\n<p>Our group had 4 papers recently accepted to the upcoming<a rel=\"noreferrer noopener\" href=\"http:\/\/www.ijcnn.org\" target=\"_blank\"> International Joint Conference on Neural Networks! <\/a>Much work on deep learning for graphs, including a novel edge-based model, an efficient graph generation approach and an explanation method for the chemical domain. Also a first proposal for an efficient federation of reservoir computing methods, part of our <a href=\"http:\/\/teaching-h2020.eu\/\">H2020 TEACHING efforts<\/a>. Preprints soon on the Arxiv!<\/p>\n\n\n\n<p><div class=\"tp_single_publication\"><span class=\"tp_single_author\">Daniele Atzeni, Davide Bacciu, Federico Errica, Alessio Micheli: <\/span> <span class=\"tp_single_title\"> Modeling Edge Features with Deep Bayesian Graph Networks<\/span>. <span class=\"tp_single_additional\"><span class=\"tp_pub_additional_booktitle\">Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021), <\/span><span class=\"tp_pub_additional_organization\">IEEE <\/span><span class=\"tp_pub_additional_publisher\">IEEE, <\/span><span class=\"tp_pub_additional_year\">2021<\/span>.<\/span><\/div><br><div class=\"tp_single_publication\"><span class=\"tp_single_author\">Danilo Numeroso, Davide Bacciu: <\/span> <span class=\"tp_single_title\">MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks<\/span>. <span class=\"tp_single_additional\"><span class=\"tp_pub_additional_booktitle\">Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021), <\/span><span class=\"tp_pub_additional_organization\">IEEE <\/span><span class=\"tp_pub_additional_year\">2021<\/span>.<\/span><\/div><br><div class=\"tp_single_publication\"><span class=\"tp_single_author\">Davide Bacciu, Daniele Di Sarli, Pouria Faraji, Claudio Gallicchio, Alessio Micheli: <\/span> <span class=\"tp_single_title\">Federated Reservoir Computing Neural Networks<\/span>. <span class=\"tp_single_additional\"><span class=\"tp_pub_additional_booktitle\">Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021), <\/span><span class=\"tp_pub_additional_publisher\">IEEE, <\/span><span class=\"tp_pub_additional_year\">2021<\/span>.<\/span><\/div><br><div class=\"tp_single_publication\"><span class=\"tp_single_author\">Davide Bacciu, Marco Podda: <\/span> <span class=\"tp_single_title\">GraphGen-Redux: a Fast and Lightweight Recurrent Model for Labeled Graph Generation<\/span>. <span class=\"tp_single_additional\"><span class=\"tp_pub_additional_booktitle\">Proceedings of the International Joint Conference on Neural Networks (IJCNN 2021), <\/span><span class=\"tp_pub_additional_organization\">IEEE <\/span><span class=\"tp_pub_additional_year\">2021<\/span>.<\/span><\/div><\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Our group had 4 papers recently accepted to the upcoming International Joint Conference on Neural Networks! Much work on deep learning for graphs, including a novel edge-based model, an efficient graph generation approach and an explanation method for the chemical domain. Also a first proposal for an efficient federation of reservoir computing methods, part of [&hellip;]<\/p>\n","protected":false},"author":19,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[10,3,13,4],"tags":[],"class_list":["post-1021","post","type-post","status-publish","format-standard","hentry","category-deep-learning-research","category-news","category-papers","category-research"],"_links":{"self":[{"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/posts\/1021","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/users\/19"}],"replies":[{"embeddable":true,"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/comments?post=1021"}],"version-history":[{"count":4,"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/posts\/1021\/revisions"}],"predecessor-version":[{"id":1026,"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/posts\/1021\/revisions\/1026"}],"wp:attachment":[{"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/media?parent=1021"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/categories?post=1021"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/pages.di.unipi.it\/bacciu\/wp-json\/wp\/v2\/tags?post=1021"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}