D
Dylan Bourgeois
Researcher at École Polytechnique Fédérale de Lausanne
Publications - 10
Citations - 744
Dylan Bourgeois is an academic researcher from École Polytechnique Fédérale de Lausanne. The author has contributed to research in topics: Set (psychology) & Selection bias. The author has an hindex of 4, co-authored 10 publications receiving 327 citations. Previous affiliations of Dylan Bourgeois include Stanford University.
Papers
More filters
Posted Content
GNNExplainer: Generating Explanations for Graph Neural Networks
TL;DR: GnExplainer is proposed, the first general, model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task.
Proceedings Article
GNNExplainer: Generating Explanations for Graph Neural Networks
TL;DR: GNNExplainer as mentioned in this paper identifies a compact subgraph structure and a small subset of node features that have a crucial role in GNN's prediction, and generates consistent and concise explanations for an entire class of instances.
Posted Content
GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks
TL;DR: GnExplainer is proposed, a general model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task (node and graph classification, link prediction).
Proceedings ArticleDOI
Selection Bias in News Coverage: Learning it, Fighting it
TL;DR: In this paper, the authors introduce a methodology to capture the latent structure of media's decision process on a large scale, and evaluate their approach on a set of events collected from the GDELT database.
Proceedings ArticleDOI
Selection Bias in News Coverage: Learning it, Fighting it
TL;DR: This work introduces a methodology to capture the latent structure of media's decision process on a large scale, shows media coverage to be predictable using personalization techniques, and proposes a method to select a set of sources by leveraging the latent representation.