Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Tomislav Duricic"'
Publikováno v:
Frontiers in Big Data, Vol 6 (2023)
By providing personalized suggestions to users, recommender systems have become essential to numerous online platforms. Collaborative filtering, particularly graph-based approaches using Graph Neural Networks (GNNs), have demonstrated great results i
Externí odkaz:
https://doaj.org/article/259c6c5a656c4bd9bd78f4e26da77ac4
Publikováno v:
Applied Network Science, Vol 6, Iss 1, Pp 1-26 (2021)
Abstract Graph Neural Networks (GNNs) are effective in many applications. Still, there is a limited understanding of the effect of common graph structures on the learning process of GNNs. To fill this gap, we study the impact of community structure a
Externí odkaz:
https://doaj.org/article/78903229e5844af9a553f1b39e1d61eb
Publikováno v:
Frontiers in Artificial Intelligence, Vol 4 (2021)
Online videos have become a prevalent means for people to acquire information. Videos, however, are often polarized, misleading, or contain topics on which people have different, contradictory views. In this work, we introduce natural language explan
Externí odkaz:
https://doaj.org/article/83089135082244ff8b3ed2bc1fcae8f5
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031282409
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da3f5e4dcbb5b8304e2caaa7a7c99fbd
https://doi.org/10.1007/978-3-031-28241-6_23
https://doi.org/10.1007/978-3-031-28241-6_23
Publikováno v:
Applied Network Science, Vol 6, Iss 1, Pp 1-26 (2021)
Graph Neural Networks (GNNs) are effective in many applications. Still, there is a limited understanding of the effect of common graph structures on the learning process of GNNs. To fill this gap, we study the impact of community structure and homoph
Publikováno v:
HT
New York, NY : Association for Computing Machinery, ACM Conferences 111-120 (2021). doi:10.1145/3465336.3475110
Proceedings of the 32nd ACM Conference on Hypertext and Social Media
Proceedings of the 32nd ACM Conference on Hypertext and Social Media32. ACM Conference on Hypertext and Social Media, HT '21, online, 2021-08-30-2021-09-02
New York, NY : Association for Computing Machinery, ACM Conferences 111-120 (2021). doi:10.1145/3465336.3475110
Proceedings of the 32nd ACM Conference on Hypertext and Social Media
Proceedings of the 32nd ACM Conference on Hypertext and Social Media32. ACM Conference on Hypertext and Social Media, HT '21, online, 2021-08-30-2021-09-02
Recent work has shown that graph neural networks (GNNs) are vulnerable to adversarial attacks on graph data. Common attack approaches are typically informed, i.e. they have access to information about node attributes such as labels and feature vector
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::550b20f321eabcad1a9182b3889748ca
http://arxiv.org/abs/2107.11327
http://arxiv.org/abs/2107.11327
Publikováno v:
Studies in Computational Intelligence ISBN: 9783030653507
COMPLEX NETWORKS (2)
COMPLEX NETWORKS (2)
Graph Neural Networks (GNNs) are effective in many applications. Still, there is a limited understanding of the effect of common graph structures on the learning process of GNNs. In this work, we systematically study the impact of community structure
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f8d14ed35cfcfcafa592edb24a6f953b
https://doi.org/10.1007/978-3-030-65351-4_2
https://doi.org/10.1007/978-3-030-65351-4_2
Homophily describes the phenomenon that similarity breeds connection, i.e., individuals tend to form ties with other people who are similar to themselves in some aspect(s). The similarity in music taste can undoubtedly influence who we make friends w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff2019ec25cf39548fcebd597b8bfdbd
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030594909
ISMIS
ISMIS
In this work, we study the utility of graph embeddings to generate latent user representations for trust-based collaborative filtering. In a cold-start setting, on three publicly available datasets, we evaluate approaches from four method families: (
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8c05a0aea561ba141352a4a4f7c066db
https://doi.org/10.1007/978-3-030-59491-6_17
https://doi.org/10.1007/978-3-030-59491-6_17
Publikováno v:
it - Information Technology. 60:219-228
A challenge for importers in the automobile industry is adjusting to rapidly changing market demands. In this work, we describe a practical study of car import planning based on the monthly car registrations in Austria. We model the task as a data dr