3 citations · 6 across the 11 of their papers we have counts for
5 papers · 1 filter
Analyzing the Effect of Embedding Norms and Singular Values to Oversmoothing in Graph Neural Networks
Dimitrios Kelesis, Dimitris Fotakis, Georgios Paliouras
In this paper, we study the factors that contribute to the effect of oversmoothing in deep Graph Neural Networks (GNNs). Specifically, our analysis is based on a new metric (Mean A…
Reducing Oversmoothing through Informed Weight Initialization in Graph Neural Networks
Dimitrios Kelesis, Dimitris Fotakis, Georgios Paliouras
In this work, we generalize the ideas of Kaiming initialization to Graph Neural Networks (GNNs) and propose a new scheme (G-Init) that reduces oversmoothing, leading to very good r…
Partially Trained Graph Convolutional Networks Resist Oversmoothing
Dimitrios Kelesis, Dimitris Fotakis, Georgios Paliouras
In this work we investigate an observation made by Kipf \& Welling, who suggested that untrained GCNs can generate meaningful node embeddings. In particular, we investigate the eff…
GLANCE: Global Actions in a Nutshell for Counterfactual Explainability
Loukas Kavouras, Eleni Psaroudaki, Konstantinos Tsopelas +9
The widespread deployment of machine learning systems in critical real-world decision-making applications has highlighted the urgent need for counterfactual explainability methods…
Fairness in Ranking: Robustness through Randomization without the Protected Attribute
Andrii Kliachkin, Eleni Psaroudaki, Jakub Marecek +1
There has been great interest in fairness in machine learning, especially in relation to classification problems. In ranking-related problems, such as in online advertising, recomm…