Graph neural networks for temporal graphs: State of the art, open challenges, and opportunities

A Longa, V Lachi, G Santin, M Bianchini, B Lepri… - arXiv preprint arXiv …, 2023 - arxiv.org
Graph Neural Networks (GNNs) have become the leading paradigm for learning on (static)
graph-structured data. However, many real-world systems are dynamic in nature, since the …

Explaining the explainers in graph neural networks: a comparative study

A Longa, S Azzolin, G Santin, G Cencetti, P Liò… - ACM Computing …, 2024 - dl.acm.org
Following a fast initial breakthrough in graph based learning, Graph Neural Networks
(GNNs) have reached a widespread application in many science and engineering fields …

The expressive power of pooling in graph neural networks

FM Bianchi, V Lachi - Advances in neural information …, 2023 - proceedings.neurips.cc
Abstract In Graph Neural Networks (GNNs), hierarchical pooling operators generate local
summaries of the data by coarsening the graph structure and the vertex features …

A survey on explainability of graph neural networks

J Kakkad, J Jannu, K Sharma, C Aggarwal… - arXiv preprint arXiv …, 2023 - arxiv.org
Graph neural networks (GNNs) are powerful graph-based deep-learning models that have
gained significant attention and demonstrated remarkable performance in various domains …

Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning

F Mumuni, A Mumuni - Cognitive Systems Research, 2024 - Elsevier
We review current and emerging knowledge-informed and brain-inspired cognitive systems
for realizing adversarial defenses, eXplainable Artificial Intelligence (XAI), and zero-shot or …

Interpretable neural-symbolic concept reasoning

P Barbiero, G Ciravegna, F Giannini… - International …, 2023 - proceedings.mlr.press
Deep learning methods are highly accurate, yet their opaque decision process prevents
them from earning full human trust. Concept-based models aim to address this issue by …

Factorized explainer for graph neural networks

R Huang, F Shirani, D Luo - Proceedings of the AAAI conference on …, 2024 - ojs.aaai.org
Graph Neural Networks (GNNs) have received increasing attention due to their ability to
learn from graph-structured data. To open the black-box of these deep learning models, post …

NCH-DDA: Neighborhood contrastive learning heterogeneous network for drug–disease association prediction

P Zhang, C Che, B Jin, J Yuan, R Li, Y Zhu - Expert Systems with …, 2024 - Elsevier
Exploring new therapeutic diseases for existing drugs plays an essential role in reducing
drug development costs. However, existing methods for predicting drug–disease association …

Generating explanations for conceptual validation of graph neural networks: An investigation of symbolic predicates learned on relevance-ranked sub-graphs

B Finzel, A Saranti, A Angerschmid, D Tafler… - KI-Künstliche …, 2022 - Springer
Abstract Graph Neural Networks (GNN) show good performance in relational data
classification. However, their contribution to concept learning and the validation of their …

State of the art and potentialities of graph-level learning

Z Yang, G Zhang, J Wu, J Yang, QZ Sheng… - ACM Computing …, 2024 - dl.acm.org
Graphs have a superior ability to represent relational data, such as chemical compounds,
proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as …