{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:36:23Z","timestamp":1761176183299,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Idempotent Generative Networks (IGNs) are deep generative models that also function as local data manifold projectors, mapping arbitrary inputs back onto the manifold. They are trained to act as identity operators on the data and as idempotent operators off the data manifold. However, IGNs suffer from mode collapse, mode dropping, and training instability due to their objectives, which contain adversarial components and can cause the model to cover the data manifold only partially \u2013 an issue shared with generative adversarial networks. We introduce Non-Adversarial Idempotent Generative Networks (NAIGNs) to address these issues. Our loss function combines reconstruction with the non-adversarial generative objective of Implicit Maximum Likelihood Estimation (IMLE). This improves on IGN\u2019s ability to restore corrupted data and generate new samples that closely match the data distribution. We moreover demonstrate that NAIGNs implicitly learn the distance field to the data manifold, as well as an energy-based model.<\/jats:p>","DOI":"10.3233\/faia251035","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:49:27Z","timestamp":1761126567000},"source":"Crossref","is-referenced-by-count":0,"title":["A Non-Adversarial Approach to Idempotent Generative Modelling"],"prefix":"10.3233","author":[{"given":"Mohammed","family":"Al-Jaff","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology"}]},{"given":"Giovanni Luca","family":"Marchetti","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}]},{"given":"Michael C.","family":"Welle","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}]},{"given":"Jens","family":"Lundell","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}]},{"given":"Mats G.","family":"Gustafsson","sequence":"additional","affiliation":[{"name":"Uppsala University"}]},{"given":"Gustav Eje","family":"Henter","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}]},{"given":"Hossein","family":"Azizpour","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}]},{"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:49:27Z","timestamp":1761126567000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251035"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251035","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}