ShapG: new feature importance method based on the Shapley value

• URL: http://arxiv.org/abs/2407.00506v2
• Date: Mon, 31 Mar 2025 06:57:08 GMT
• Title: ShapG: new feature importance method based on the Shapley value
• Authors: Chi Zhao, Jing Liu, Elena Parilina,
• Abstract summary: We propose a new Explainable Artificial Intelligence (XAI) method called ShapG (Explanations based on Shapley value for Graphs) for measuring feature importance.<n>At the first stage, it defines an undirected graph based on the dataset, where nodes represent features and edges are added.<n>At the second stage, it calculates an approximated Shapley value by sampling the data taking into account this graph structure.
• Score: 3.411077163447709
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With wide application of Artificial Intelligence (AI), it has become particularly important to make decisions of AI systems explainable and transparent. In this paper, we proposed a new Explainable Artificial Intelligence (XAI) method called ShapG (Explanations based on Shapley value for Graphs) for measuring feature importance. ShapG is a model-agnostic global explanation method. At the first stage, it defines an undirected graph based on the dataset, where nodes represent features and edges are added based on calculation of correlation coefficients between features. At the second stage, it calculates an approximated Shapley value by sampling the data taking into account this graph structure. The sampling approach of ShapG allows to calculate the importance of features efficiently, i.e. to reduce computational complexity. Comparison of ShapG with other existing XAI methods shows that it provides more accurate explanations for two examined datasets. We also compared other XAI methods developed based on cooperative game theory with ShapG in running time, and the results show that ShapG exhibits obvious advantages in its running time, which further proves efficiency of ShapG. In addition, extensive experiments demonstrate a wide range of applicability of the ShapG method for explaining complex models. We find ShapG an important tool in improving explainability and transparency of AI systems and believe it can be widely used in various fields.

Related papers

• ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees [3.7098626170498643]
  Pixel-level feature attributions are an important tool in eXplainable AI for Computer Vision (XCV)<n>This paper introduces ShapBPT, a novel data-aware XCV method based on the hierarchical Shapley formula.<n>By using this data-aware hierarchical partitioning, ShapBPT ensures that feature attributions align with intrinsic image data.
  arXiv  Detail & Related papers  (2026-02-04T10:42:21Z)
• QGShap: Quantum Acceleration for Faithful GNN Explanations [0.48998185508205744]
  We introduce QGShap, a quantum computing approach that leverages amplitude amplification to achieve quadratic speedups in coalition evaluation.<n>Unlike classical sampling or surrogate methods, our approach provides fully faithful explanations without approximation trade-offs for tractable graph sizes.
  arXiv  Detail & Related papers  (2025-12-01T16:19:15Z)
• From Abstract to Actionable: Pairwise Shapley Values for Explainable AI [0.8192907805418583]
  We propose Pairwise Shapley Values, a novel framework that grounds feature attributions in explicit, human-relatable comparisons. Our method introduces pairwise reference selection combined with single-value imputation to deliver intuitive, model-agnostic explanations. We demonstrate that Pairwise Shapley Values enhance interpretability across diverse regression and classification scenarios.
  arXiv  Detail & Related papers  (2025-02-18T04:20:18Z)
• Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks [53.10674067060148]
  Shapley Interactions (SIs) quantify node contributions and interactions among multiple nodes. By exploiting the GNN architecture, we show that the structure of interactions in node embeddings are preserved for graph prediction. We introduce GraphSHAP-IQ, an efficient approach to compute any-order SIs exactly.
  arXiv  Detail & Related papers  (2025-01-28T13:37:44Z)
• shapiq: Shapley Interactions for Machine Learning [21.939393765684827]
  We introduce shapiq, an open-source Python package that unifies state-of-the-art algorithms to efficiently compute Shapley Value (SV) and Shapley Interactions (SIs) For practitioners, shapiq is able to explain and visualize any-order feature interactions in predictions of models, including vision transformers, language models, as well as XGBoost and LightGBM with TreeShap-IQ.
  arXiv  Detail & Related papers  (2024-10-02T15:16:53Z)
• Fast Shapley Value Estimation: A Unified Approach [71.92014859992263]
  We propose a straightforward and efficient Shapley estimator, SimSHAP, by eliminating redundant techniques. In our analysis of existing approaches, we observe that estimators can be unified as a linear transformation of randomly summed values from feature subsets. Our experiments validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values.
  arXiv  Detail & Related papers  (2023-11-02T06:09:24Z)
• Generalizing Backpropagation for Gradient-Based Interpretability [103.2998254573497]
  We show that the gradient of a model is a special case of a more general formulation using semirings. This observation allows us to generalize the backpropagation algorithm to efficiently compute other interpretable statistics.
  arXiv  Detail & Related papers  (2023-07-06T15:19:53Z)
• Grouping Shapley Value Feature Importances of Random Forests for explainable Yield Prediction [0.8543936047647136]
  We explain the concept of Shapley values directly computed for groups of features and introduce an algorithm to compute them efficiently on tree structures. We provide a blueprint for designing swarm plots that combine many local explanations for global understanding.
  arXiv  Detail & Related papers  (2023-04-14T13:03:33Z)
• Localized Contrastive Learning on Graphs [110.54606263711385]
  We introduce a simple yet effective contrastive model named Localized Graph Contrastive Learning (Local-GCL) In spite of its simplicity, Local-GCL achieves quite competitive performance in self-supervised node representation learning tasks on graphs with various scales and properties.
  arXiv  Detail & Related papers  (2022-12-08T23:36:00Z)
• ProjB: An Improved Bilinear Biased ProjE model for Knowledge Graph Completion [1.5576879053213302]
  This work improves on ProjE KGE due to low computational complexity and high potential for model improvement. Experimental results on benchmark Knowledge Graphs (KGs) such as FB15K and WN18 show that the proposed approach outperforms the state-of-the-art models in entity prediction task.
  arXiv  Detail & Related papers  (2022-08-15T18:18:05Z)
• Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospital [0.11470070927586014]
  We propose two novel techniques for better interpretability of machine learning models. We show how the A/G ratio works as an important prognostic factor for cerebral infarction using our hospital data and proposed techniques.
  arXiv  Detail & Related papers  (2021-12-21T10:08:31Z)
• Dist2Cycle: A Simplicial Neural Network for Homology Localization [66.15805004725809]
  Simplicial complexes can be viewed as high dimensional generalizations of graphs that explicitly encode multi-way ordered relations. We propose a graph convolutional model for learning functions parametrized by the $k$-homological features of simplicial complexes.
  arXiv  Detail & Related papers  (2021-10-28T14:59:41Z)
• Fast Hierarchical Games for Image Explanations [78.16853337149871]
  We present a model-agnostic explanation method for image classification based on a hierarchical extension of Shapley coefficients. Unlike other Shapley-based explanation methods, h-Shap is scalable and can be computed without the need of approximation. We compare our hierarchical approach with popular Shapley-based and non-Shapley-based methods on a synthetic dataset, a medical imaging scenario, and a general computer vision problem.
  arXiv  Detail & Related papers  (2021-04-13T13:11:02Z)
• Deep Reinforcement Learning of Graph Matching [63.469961545293756]
  Graph matching (GM) under node and pairwise constraints has been a building block in areas from optimization to computer vision. We present a reinforcement learning solver for GM i.e. RGM that seeks the node correspondence between pairwise graphs. Our method differs from the previous deep graph matching model in the sense that they are focused on the front-end feature extraction and affinity function learning.
  arXiv  Detail & Related papers  (2020-12-16T13:48:48Z)

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.