Immediate Split Trees: Immediate Encoding of Floating Point Split Values in Random Forests

Autor: Hakert, Christian, Chen, Kuan-Hsun, Chen, Jian-Jia, Amini, Massih-Reza, Canu, Stéphane, Fischer, Asja, Guns, Tias, Kralj Novak, Petra, Tsoumakas, Grigorios

Publikováno v: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2022, Grenoble, France, September 19–23, 2022, Proceedings, Part V, 531-546
STARTPAGE=531;ENDPAGE=546;TITLE=Machine Learning and Knowledge Discovery in Databases

Random forests and decision trees are increasingly interesting candidates for resource-constrained machine learning models. In order to make the execution of these models efficient under resource limitations, various optimized implementations have be

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=narcis______::c974883a67007cd7619c65ae3eb5ff3d
https://research.utwente.nl/en/publications/ddc1fe7d-56e5-4a39-b84a-f2c36348bcb1

Hop-Count Based Self-supervised Anomaly Detection on Attributed Networks

Autor: Huang, Tianjin, Pei, Yulong, Menkovski, Vlado, Pechenizkiy, Mykola, Amini, Massih-Reza, Canu, Stéphane, Fischer, Asja, Guns, Tias, Kralj Novak, Petra, Tsoumakas, Grigorios

Publikováno v: Machine Learning and Knowledge Discovery in Databases-European Conference, ECML PKDD 2022, Proceedings, 225-241
STARTPAGE=225;ENDPAGE=241;TITLE=Machine Learning and Knowledge Discovery in Databases-European Conference, ECML PKDD 2022, Proceedings
Machine Learning and Knowledge Discovery in Databases ISBN: 9783031263866

A number of approaches for anomaly detection on attributed networks have been proposed. However, most of them suffer from two major limitations: (1) they rely on unsupervised approaches which are intrinsically less effective due to the lack of superv

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::979a555314529ea08f3e00784d16c814
https://research.tue.nl/nl/publications/e11d0061-73b6-4865-90de-6d5a619fd4c1

Ensemble Clustering for Novelty Detection in Data Streams

Autor: Garcia, Kemilly Dearo, de Faria, Elaine Ribeiro, de Sá, Cláudio Rebelo, Mendes-Moreira, João, Aggarwal, Charu C., de Carvalho, André C.P.L.F., Kok, Joost N., Kralj Novak, Petra, Džeroski, Sašo, Šmuc, Tomislav

Publikováno v: Discovery Science ISBN: 9783030337773
DS
Discovery Science: 22nd International Conference, DS 2019, Splitm, Croatia, October 28-30, 2019. Proceedings, 460-470
STARTPAGE=460;ENDPAGE=470;TITLE=Discovery Science

In data streams new classes can appear over time due to changes in the data statistical distribution. Consequently, models can become outdated, which requires the use of incremental learning algorithms capable of detecting and learning the changes ov

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82638504d239d588302fb9c4ae2ab8e5
http://www.scopus.com/inward/record.url?scp=85075818430&partnerID=8YFLogxK

Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift

Autor: Martinc, Matej, Kralj Novak, Petra, Pollak, Senja

Publikováno v: Proceedings of the 12th Language Resources and Evaluation Conference (LREC2020)

We propose a new method that leverages contextual embeddings for the task of diachronic semantic shift detection by generating time specific word representations from BERT embeddings. The results of our experiments in the domain specific LiverpoolFC

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::466c60bc0385d8a45e13aebd0d5ae30a

Evolution of topics and hate speech in retweet network communities.

Autor: Evkoski, Bojan, Ljubešić, Nikola, Pelicon, Andraž, Mozetič, Igor, Kralj Novak, Petra

Publikováno v: Applied Network Science; 1/18/2022, Vol. 6 Issue 1, p1-20, 20p