Private Graph Extraction via Feature Explanations

1 code implementation • 29 Jun 2022 • Iyiola E. Olatunji, Mandeep Rathee, Thorben Funke, Megha Khosla

Based on the different kinds of auxiliary information available to the adversary, we propose several graph reconstruction attacks.

BIG-bench Machine Learning Graph Reconstruction

BAGEL: A Benchmark for Assessing Graph Neural Network Explanations

1 code implementation • 28 Jun 2022 • Mandeep Rathee, Thorben Funke, Avishek Anand, Megha Khosla

Given a GNN model, several interpretability approaches exist to explain GNN models with diverse (sometimes conflicting) evaluation methodologies.

BIG-bench Machine Learning Graph Classification

Learnt Sparsification for Interpretable Graph Neural Networks

no code implementations • 23 Jun 2021 • Mandeep Rathee, Zijian Zhang, Thorben Funke, Megha Khosla, Avishek Anand

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

1 code implementation • 18 May 2021 • Thorben Funke, Megha Khosla, Mandeep Rathee, Avishek Anand

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.

Attribute Explanation Generation +1