Search Results for author:
Found 8 papers, 5 papers with code
Private Graph Extraction via Feature Explanations
Based on the different kinds of auxiliary information available to the adversary, we propose several graph reconstruction attacks.
BAGEL: A Benchmark for Assessing Graph Neural Network Explanations
Given a GNN model, several interpretability approaches exist to explain GNN models with diverse (sometimes conflicting) evaluation methodologies.
Releasing Graph Neural Networks with Differential Privacy Guarantees
With the increasing popularity of graph neural networks (GNNs) in several sensitive applications like healthcare and medicine, concerns have been raised over the privacy aspects of trained GNNs.
An Adaptive Clustering Approach for Accident Prediction
ACAP applies adaptive clustering to the observed geospatial accident distribution and performs embeddings of temporal, accident-related, and regional features to increase prediction accuracy.
Learnt Sparsification for Interpretable Graph Neural Networks
However, GNNs remain hard to interpret as the interplay between node features and graph structure is only implicitly learned.
Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks
In this paper, we lay down some of the fundamental principles that an explanation method for graph neural networks should follow and introduce a metric RDT-Fidelity as a measure of the explanation's effectiveness.
Hard Masking for Explaining Graph Neural Networks
Graph Neural Networks (GNNs) are a flexible and powerful family of models that build nodes' representations on irregular graph-structured data.
Low-dimensional statistical manifold embedding of directed graphs
We propose a novel node embedding of directed graphs to statistical manifolds, which is based on a global minimization of pairwise relative entropy and graph geodesics in a non-linear way.
