Zobrazeno 1 - 10
of 169
pro vyhledávání: '"Boström, Henrik"'
Autor:
Alkhatib, Amr, Boström, Henrik
Many machine learning algorithms for tabular data produce black-box models, which prevent users from understanding the rationale behind the model predictions. In their unconstrained form, graph neural networks fall into this category, and they have f
Externí odkaz:
http://arxiv.org/abs/2408.07661
Publikováno v:
In: Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13713. Springer, Cham (2023)
Characteristic rules have been advocated for their ability to improve interpretability over discriminative rules within the area of rule learning. However, the former type of rule has not yet been used by techniques for explaining predictions. A nove
Externí odkaz:
http://arxiv.org/abs/2405.21003
Autor:
Abbahaddou, Yassine, Ennadir, Sofiane, Lutzeyer, Johannes F., Vazirgiannis, Michalis, Boström, Henrik
Graph Neural Networks (GNNs) have demonstrated state-of-the-art performance in various graph representation learning tasks. Recently, studies revealed their vulnerability to adversarial attacks. In this work, we theoretically define the concept of ex
Externí odkaz:
http://arxiv.org/abs/2404.17947
Autor:
Ennadir, Sofiane, Abbahaddou, Yassine, Lutzeyer, Johannes F., Vazirgiannis, Michalis, Boström, Henrik
Graph Neural Networks (GNNs) have emerged as the dominant approach for machine learning on graph-structured data. However, concerns have arisen regarding the vulnerability of GNNs to small adversarial perturbations. Existing defense methods against s
Externí odkaz:
http://arxiv.org/abs/2402.13987
Autor:
Boström, Henrik
A random forest prediction can be computed by the scalar product of the labels of the training examples and a set of weights that are determined by the leafs of the forest into which the test object falls; each prediction can hence be explained exact
Externí odkaz:
http://arxiv.org/abs/2311.14581
Autor:
Boström, Henrik, Högardh, Jenny
Bakgrund: Försämrade sömnvanor hos ungdomar är idag ett växande folkhälsoproblem som ökar både nationellt och internationellt. Ungdomar sover idag i genomsnitt mindre än åtta timmar per natt vilket kan leda till ohälsa. Syftet: Syftet med
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-51906
Publikováno v:
Proceedings of Machine Learning Research (PMLR) Volume 204, Year 2023
Score-based explainable machine-learning techniques are often used to understand the logic behind black-box models. However, such explanation techniques are often computationally expensive, which limits their application in time-critical contexts. Th
Externí odkaz:
http://arxiv.org/abs/2308.11975
Data in tabular format is frequently occurring in real-world applications. Graph Neural Networks (GNNs) have recently been extended to effectively handle such data, allowing feature interactions to be captured through representation learning. However
Externí odkaz:
http://arxiv.org/abs/2308.08945
Image matching is a key component of many tasks in computer vision and its main objective is to find correspondences between features extracted from different natural images. When images are represented as graphs, image matching boils down to the pro
Externí odkaz:
http://arxiv.org/abs/2205.14275