Graph-Based Explainable AI: A Comprehensive Survey - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail (Preprint/Prepublication) Année : 2014

Graph-Based Explainable AI: A Comprehensive Survey

Résumé

Graph-based learning models learn structure-aware and node-level representations through relational associations between data points, enhancing predictions and explainability. The ability of Graph Neural Network (GNN) models to learn from non-Euclidean spaces, has shifted explainability efforts towards GNNs, neglecting other significant methodologies. This survey addresses this gap by including traditional machine learning and deep learning models, based on Reinforcement Learning, Multi-Hop Reasoning, Knowledge Graphs, and GNNs. It proposes a hierarchical categorization of graph explanation models based on explanation modalities and approaches. Furthermore, it examines the merits, drawbacks, and suitability of each strategy across domains and tasks followed by future research directions.
Fichier principal
Vignette du fichier
Graph_Based_Explainable_AI____HAL_version.pdf (1020.32 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04660442 , version 1 (23-07-2024)

Licence

Identifiants

  • HAL Id : hal-04660442 , version 1

Citer

Margarita Bugueño, Russa Biswas, Gerard de Melo. Graph-Based Explainable AI: A Comprehensive Survey. 2024. ⟨hal-04660442⟩
73 Consultations
75 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More