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

• URL: http://arxiv.org/abs/2505.22252v1
• Date: Wed, 28 May 2025 11:40:48 GMT
• Title: B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data
• Authors: Magdalena Proszewska, Tomasz Danel, Dawid Rymarczyk,
• Abstract summary: B-XAIC is a novel benchmark constructed from real-world molecular data and diverse tasks with known ground-truth rationales for assigned labels.<n>This benchmark provides a valuable resource for gaining deeper insights into the faithfulness of XAI, facilitating the development of more reliable and interpretable models.
• Score: 4.945980414437814
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Understanding the reasoning behind deep learning model predictions is crucial in cheminformatics and drug discovery, where molecular design determines their properties. However, current evaluation frameworks for Explainable AI (XAI) in this domain often rely on artificial datasets or simplified tasks, employing data-derived metrics that fail to capture the complexity of real-world scenarios and lack a direct link to explanation faithfulness. To address this, we introduce B-XAIC, a novel benchmark constructed from real-world molecular data and diverse tasks with known ground-truth rationales for assigned labels. Through a comprehensive evaluation using B-XAIC, we reveal limitations of existing XAI methods for Graph Neural Networks (GNNs) in the molecular domain. This benchmark provides a valuable resource for gaining deeper insights into the faithfulness of XAI, facilitating the development of more reliable and interpretable models.

Related papers

• Robust Molecular Property Prediction via Densifying Scarce Labeled Data [51.55434084913129]
  In drug discovery, compounds most critical for advancing research often lie beyond the training set.<n>We propose a novel meta-learning-based approach that leverages unlabeled data to interpolate between in-distribution (ID) and out-of-distribution (OOD) data.<n>We demonstrate significant performance gains on challenging real-world datasets.
  arXiv  Detail & Related papers  (2025-06-13T15:27:40Z)
• Addressing the Scarcity of Benchmarks for Graph XAI [6.387263468033964]
  We propose a general method to automate the construction of XAI benchmarks for graph classification from real-world datasets.<n>We provide both 15 ready-made benchmarks, as well as the code to generate more than 2000 additional XAI benchmarks with our method.
  arXiv  Detail & Related papers  (2025-05-18T14:19:52Z)
• VirtualXAI: A User-Centric Framework for Explainability Assessment Leveraging GPT-Generated Personas [0.07499722271664146]
  The demand for eXplainable AI (XAI) has increased to enhance the interpretability, transparency, and trustworthiness of AI models.<n>We propose a framework that integrates quantitative benchmarking with qualitative user assessments through virtual personas.<n>This yields an estimated XAI score and provides tailored recommendations for both the optimal AI model and the XAI method for a given scenario.
  arXiv  Detail & Related papers  (2025-03-06T09:44:18Z)
• Extracting human interpretable structure-property relationships in chemistry using XAI and large language models [0.4769602527256662]
  We propose the XpertAI framework that integrates XAI methods with large language models (LLMs) accessing scientific literature to generate natural language explanations of raw chemical data automatically. Our results show that XpertAI combines the strengths of LLMs and XAI tools in generating specific, scientific, and interpretable explanations.
  arXiv  Detail & Related papers  (2023-11-07T15:02:32Z)
• Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability [70.60433013657693]
  Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level. We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
  arXiv  Detail & Related papers  (2023-06-14T23:24:01Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• Inducing Gaussian Process Networks [80.40892394020797]
  We propose inducing Gaussian process networks (IGN), a simple framework for simultaneously learning the feature space as well as the inducing points. The inducing points, in particular, are learned directly in the feature space, enabling a seamless representation of complex structured domains. We report on experimental results for real-world data sets showing that IGNs provide significant advances over state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-21T05:27:09Z)
• Handling Distribution Shifts on Graphs: An Invariance Perspective [78.31180235269035]
  We formulate the OOD problem on graphs and develop a new invariant learning approach, Explore-to-Extrapolate Risk Minimization (EERM) EERM resorts to multiple context explorers that are adversarially trained to maximize the variance of risks from multiple virtual environments. We prove the validity of our method by theoretically showing its guarantee of a valid OOD solution.
  arXiv  Detail & Related papers  (2022-02-05T02:31:01Z)
• Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction [2.8544822698499255]
  Graph neural networks (GNNs) remain of limited acceptance in drug discovery due to their lack of interpretability. In this work, we build three levels of benchmark datasets to quantitatively assess the interpretability of the state-of-the-art GNN models. We implement recent XAI methods in combination with different GNN algorithms to highlight the benefits, limitations, and future opportunities for drug discovery.
  arXiv  Detail & Related papers  (2021-07-01T04:49:29Z)
• Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Dataset [0.05156484100374058]
  We provide a framework to generate attribution benchmark datasets for regression problems in the geosciences. We train a fully-connected network to learn the underlying function that was used for simulation. We compare estimated attribution heatmaps from different XAI methods to the ground truth in order to identify examples where specific XAI methods perform well or poorly.
  arXiv  Detail & Related papers  (2021-03-18T03:39:17Z)
• Graph Representation Learning via Graphical Mutual Information Maximization [86.32278001019854]
  We propose a novel concept, Graphical Mutual Information (GMI), to measure the correlation between input graphs and high-level hidden representations. We develop an unsupervised learning model trained by maximizing GMI between the input and output of a graph neural encoder.
  arXiv  Detail & Related papers  (2020-02-04T08:33:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.