Skip to main navigation Skip to search Skip to main content

Bagel: A Benchmark for Assessing Graph Neural Network Explanations

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

Evaluating interpretability approaches for graph neural networks (GNN) specifically is known to be challenging due to the lack of a commonly accepted benchmark. Given a GNN model, several interpretability approaches exist to explain GNN models with diverse (sometimes conflicting) evaluation methodologies. In this paper, we propose a benchmark for evaluating the explainability approaches for GNNs called Bagel. In Bagel, we first propose four diverse GNN explanation evaluation regimes – 1) faithfulness, 2) sparsity, 3) correctness, and 4) plausibility. We reconcile multiple evaluation metrics in the existing literature and cover diverse notions for a holistic evaluation. Our graph datasets range from citation networks and document graphs to graphs from molecules and proteins. We conduct an extensive empirical study on four GNN models and nine post-hoc explanation approaches for node and graph classification tasks. We release both the benchmarks and reference implementations and make them available at https://github.com/Mandeep-Rathee/Bagel-benchmark.
Original languageEnglish
Title of host publicationMachine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2024, Revised Selected Papers
EditorsMattia Cerrato, Danguole Kalinauskaite, Mantas Lukoševicius, Kristina Šutiene, Mykola Pechenizkiy
Place of PublicationCham
PublisherSpringer
Pages27-42
Number of pages16
ISBN (Print)9783032253040
DOIs
Publication statusPublished - 2026
EventEuropean Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2024 - Vilnius, Lithuania
Duration: 9 Sept 202413 Sept 2024

Publication series

NameCommunications in Computer and Information Science
PublisherSpringer
Volume2559 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

ConferenceEuropean Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2024
Country/TerritoryLithuania
CityVilnius
Period9/09/2413/09/24

Keywords

  • Explainability
  • Graph Neural Networks
  • Interpretability

Fingerprint

Dive into the research topics of 'Bagel: A Benchmark for Assessing Graph Neural Network Explanations'. Together they form a unique fingerprint.

Cite this