1 citations · 1 across the 10 of their papers we have counts for
3 papers · 1 filter
Introspection in Learned Semantic Scene Graph Localisation
Manshika Charvi Bissessur, Efimia Panagiotaki, Daniele De Martini
This work investigates how semantics influence localisation performance and robustness in a learned self-supervised, contrastive semantic localisation framework. After training a l…
Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning
Alex Schutz, Victor-Alexandru Darvariu, Efimia Panagiotaki +2
Neural algorithmic reasoning (NAR) is a paradigm that trains neural networks to execute classic algorithms by supervised learning. Despite its successes, important limitations rema…
Semantic Interpretation and Validation of Graph Attention-based Explanations for GNN Models
Efimia Panagiotaki, Daniele De Martini, Lars Kunze
In this work, we propose a methodology for investigating the use of semantic attention to enhance the explainability of Graph Neural Network (GNN)-based models. Graph Deep Learning…