← Back to all news
arXiv Machine Learning By Magdalena Proszewska, Tomasz Danel, Antoni Antoszek, Dawid Rymarczyk

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

Read the original on arXiv Machine Learning →

The paper introduces B-XAIC, a benchmark for evaluating Explainable AI methods on Graph Neural Networks using real-world chemical data. It addresses shortcomings of previous frameworks that rely on artificial datasets and lack direct links to explanation faithfulness. By providing diverse tasks with known ground-truth rationales, B-XAIC enables a comprehensive assessment of XAI methods in the molecular domain.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 3

WOMBAT: Whitebox Oracle for Molecular Benchmarking and Attribution Testing

WOMBAT is a benchmark comprising 14 whitebox graph neural networks (GNNs) whose message‑passing weights are manually set to detect specific SMARTS motifs. Each model’s decision rule is explicitly known, providing a ground truth for attribution that allows researchers to identify and study errors in post‑hoc explainers such as GNNExplainer, PGExplainer, and Integrated Gradients. The authors validate the models on millions of PubChem molecules, demonstrate how Integrated Gradients can be misled to spread attribution, and release the dataset, models, and evaluation code for future XAI tool development.

By Dominik Matuszek, Bartosz Zieli\'nski, Tomasz Danel, Dawid Rymarczyk
benchmarks
More like this →
arXiv Machine Learning
Oct 22

Fragment-Level Graph Encoding for Interpretable Molecular Property Prediction

The paper introduces a fragment‑level graph encoding for molecular property prediction, using BRICS decomposition to represent molecules as graphs of synthetically meaningful fragments. This change of input representation allows any message‑passing GNN and post‑hoc attribution method to produce explanations at the functional‑group level, matching atom‑level accuracy on smaller graphs. Experiments across multiple architectures, tasks, and explainers show that fragment‑level encoding recovers known pharmacophores more reliably than post‑hoc aggregation of atom‑level explanations.

By Rafael Lopes Almeida (School of Pharmacy, University of Eastern Finland, Kuopio, Finland), Ina P\"ohner (School of Pharmacy, University of Eastern Finland, Kuopio, Finland)
More like this →
arXiv Machine Learning
Jul 3

An Additive MLP-GNN Framework for Characterizing Chemical and Structural Contributions to Aqueous Solubility

arXiv:2607. 02212v1 Announce Type: cross Abstract: Aqueous solubility is a key property in early-stage drug discovery, but most predictive models merge physicochemical descriptors and molecular graph information into a single representation, obscuring whether a prediction is driven by global chemistry, molecular structure, or both.

By Sampreeti Bhattacharya, Arkaprava Roy
ragfine-tuning
More like this →