Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Lutzeyer, Johannes F."'
Autor:
Doerr, Benjamin, Lutzeyer, Johannes F.
In recent work, Lissovoi, Oliveto, and Warwicker (Artificial Intelligence (2023)) proved that the Move Acceptance Hyper-Heuristic (MAHH) leaves the local optimum of the multimodal CLIFF benchmark with remarkable efficiency. The $O(n^3)$ runtime of th
Externí odkaz:
http://arxiv.org/abs/2407.14237
Message passing neural networks (MPNNs) have been shown to have limitations in terms of expressivity and modeling long-range interactions. Augmenting MPNNs with a virtual node (VN) removes the locality constraint of the layer aggregation and has been
Externí odkaz:
http://arxiv.org/abs/2405.13526
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:
Salha-Galvan, Guillaume, Lutzeyer, Johannes F., Dasoulas, George, Hennequin, Romain, Vazirgiannis, Michalis
Graph autoencoders (GAE) and variational graph autoencoders (VGAE) emerged as powerful methods for link prediction (LP). Their performances are less impressive on community detection (CD), where they are often outperformed by simpler alternatives suc
Externí odkaz:
http://arxiv.org/abs/2211.08972
Graph Neural Networks (GNNs) have achieved great successes in many learning tasks performed on graph structures. Nonetheless, to propagate information GNNs rely on a message passing scheme which can become prohibitively expensive when working with in
Externí odkaz:
http://arxiv.org/abs/2211.04248
Graph Neural Networks (GNNs) have been successfully used in many problems involving graph-structured data, achieving state-of-the-art performance. GNNs typically employ a message-passing scheme, in which every node aggregates information from its nei
Externí odkaz:
http://arxiv.org/abs/2204.05351
Autor:
Salha-Galvan, Guillaume, Lutzeyer, Johannes F., Dasoulas, George, Hennequin, Romain, Vazirgiannis, Michalis
Graph autoencoders (GAE) and variational graph autoencoders (VGAE) emerged as powerful methods for link prediction. Their performances are less impressive on community detection problems where, according to recent and concurring experimental evaluati
Externí odkaz:
http://arxiv.org/abs/2202.00961
The robustness of the much-used Graph Convolutional Networks (GCNs) to perturbations of their input is becoming a topic of increasing importance. In this paper, the random GCN is introduced for which a random matrix theory analysis is possible. This
Externí odkaz:
http://arxiv.org/abs/2109.01785
Message-Passing Neural Networks (MPNNs), the most prominent Graph Neural Network (GNN) framework, celebrate much success in the analysis of graph-structured data. Concurrently, the sparsification of Neural Network models attracts a great amount of ac
Externí odkaz:
http://arxiv.org/abs/2109.00909