paper-with-me

홈 › Papers

Do intermediate feature coalitions aid explainability of black-box models?

2023-03-21 · Minal Suresh Patil, Kary Främling

This work introduces the notion of intermediate concepts based on levels structure to aid explainability for black-box models. The levels structure is a hierarchical structure in which each level corresponds to features of a dataset (i.e., a player-set partition). The level of coarseness increases from the trivial set, which only comprises singletons, to the set, which only contains the grand coalition. In addition, it is possible to establish meronomies, i.e., part-whole relationships, via a domain expert that can be utilised to generate explanations at an abstract level. We illustrate the usability of this approach in a real-world car model example and the Titanic dataset, where intermediate concepts aid in explainability at different levels of abstraction.

📄 PDF Abstract BibTeX arXiv:2303.11920

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Explainable Graph Neural Networks via Structural Externalities

2025-07-19 · Lijun Wu, Dong Hao, Zhiyi Fan arxiv

Graph Neural Networks (GNNs) have achieved outstanding performance across a wide range of graph-related tasks. However, their "black-box" nature poses significant challenges to their explainability, and existing methods …

GISExplainer: On Explainability of Graph Neural Networks via Game-theoretic Interaction Subgraphs

2024-09-24 · Xingping Xian, Jianlu Liu, Chao Wang, Tao Wu 외

Explainability is crucial for the application of black-box Graph Neural Networks (GNNs) in critical fields such as healthcare, finance, cybersecurity, and more. Various feature attribution methods, especially the perturb…

Computational EfficiencyNode Classification

Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selection

2023-12-19 · Gwladys Kelodjou, Laurence Rozé, Véronique Masson, Luis Galárraga 외

Machine learning techniques, such as deep learning and ensemble methods, are widely used in various domains due to their ability to handle complex real-world tasks. However, their black-box nature has raised multiple con…

Decision MakingFairness

Building Trust in Black-box Optimization: A Comprehensive Framework for Explainability

2024-10-18 · Nazanin Nezami, Hadis Anahideh

Optimizing costly black-box functions within a constrained evaluation budget presents significant challenges in many real-world applications. Surrogate Optimization (SO) is a common resolution, yet its proprietary nature…

Feature Importance

FlowX: Towards Explainable Graph Neural Networks via Message Flows

2022-06-26 · Shurui Gui, Hao Yuan, Jie Wang, Qicheng Lao 외

We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms. While most current methods focus on explaining graph nodes, edges, or features, we argue that, as t…

Philosophy