Trustworthy Convolutional Neural Networks: A Gradient Penalized-based Approach

Autor: Halliwell, Nicholas, Lecue, Freddy

Convolutional neural networks (CNNs) are commonly used for image classification. Saliency methods are examples of approaches that can be used to interpret CNNs post hoc, identifying the most relevant pixels for a prediction following the gradients fl

Externí odkaz: http://arxiv.org/abs/2009.14260

Impact of Injecting Ground Truth Explanations on Relational Graph Convolutional Networks and their Explanation Methods for Link Prediction on Knowledge Graphs

Autor: Halliwell, Nicholas, Gandon, Fabien, Lecue, Freddy

Publikováno v: WI-IAT 2022-The 21st IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology
WI-IAT 2022-The 21st IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, Nov 2022, Niagara Falls / Hybrid, Canada

International audience; Relational Graph Convolutional Networks (RGCNs) are commonly applied to Knowledge Graphs (KGs) for black box link prediction. Several algorithms, or explanations methods, have been proposed to explain the predictions of this m

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ce4773a3046b79bd2ca656d907faf80b
https://hal.science/hal-03771424

Evaluation d'explications pour la prédiction de liens dans les graphes de connaissances par des réseaux convolutifs

Autor: Gandon, Fabien, Halliwell, Nicholas, Lecue, Freddy

Publikováno v: Ingénierie des Connaissances 2022-IC 2022-PFIA 2022
Ingénierie des Connaissances 2022-IC 2022-PFIA 2022, Jun 2022, Saint-Etienne, France

National audience; Nous résumons ici notre article à KCAP dont l'approche permet de générer un jeu de test comparatif et fournit des métriques pour évaluer les explications de prédictions de liens dans les graphes de connaissances par des rés

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::21e43074ab49a15993cd249a1a6ba076
https://inria.hal.science/hal-03927901/file/Gandon_et_al_IC_2022.pdf

A Simplified Benchmark for Non-ambiguous Explanations of Knowledge Graph Link Prediction using Relational Graph Convolutional Networks

Autor: Halliwell, Nicholas, Gandon, Fabien, Lecue, Freddy

Publikováno v: International Semantic Web Conference
International Semantic Web Conference, Oct 2021, Troy, United States
ISWC 2021-International Semantic Web Conference
ISWC 2021-International Semantic Web Conference, Oct 2021, Troy, United States. Proceedings of International Semantic Web Conference

International audience; Relational Graph Convolutional Networks (RGCNs) identify relationships within a Knowledge Graph to learn real-valued embeddings for each node and edge. Recently, researchers have proposed explanation methods to interpret the p

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1f513041386e25dd35055fbf7c56c7d1
https://hal.archives-ouvertes.fr/hal-03339562v2/document

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.