Graphs

B-XAIC

Introduced in B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data2025

About this Dataset

B-XAIC consists of 50K small molecules represented as graphs and includes 7 graph classification tasks, each with ground truth labels and corresponding explanations.

Source: B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data

Dataset Variants

B-XAIC

Papers1

B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data

B-XAIC is introduced, a novel benchmark constructed from real-world molecular data and diverse tasks with known ground-truth rationales for assigned labels that reveals limitations of existing XAI methods for Graph Neural Networks (GNNs) in the molecular domain.

Tasks

EDIT

Classification Graph Classification Explainable Artificial Intelligence (XAI)Explainable Models

Similar Datasets

DBpedia

Citeseer

Cora

Statistics

Papers

1

Tasks

0

Introduced

2025

License

cc-by-sa-4.0

Modalities

Graphs