GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks

• URL: http://arxiv.org/abs/2603.15373v1
• Date: Mon, 16 Mar 2026 14:49:48 GMT
• Title: GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networks
• Abstract summary: Two major XAI paradigms, counterfactual explanations (CFX) and feature attribution (FA) serve distinct roles in model interpretability.<n>This study introduces GradCFA, a hybrid framework combining CFX and FA to improve interpretability.
• Score: 18.934170239661363
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Explainable Artificial Intelligence (XAI) is increasingly essential as AI systems are deployed in critical fields such as healthcare and finance, offering transparency into AI-driven decisions. Two major XAI paradigms, counterfactual explanations (CFX) and feature attribution (FA), serve distinct roles in model interpretability. This study introduces GradCFA, a hybrid framework combining CFX and FA to improve interpretability by explicitly optimizing feasibility, plausibility, and diversity - key qualities often unbalanced in existing methods. Unlike most CFX research focused on binary classification, GradCFA extends to multi-class scenarios, supporting a wider range of applications. We evaluate GradCFA's validity, proximity, sparsity, plausibility, and diversity against state-of-the-art methods, including Wachter, DiCE, CARE for CFX, and SHAP for FA. Results show GradCFA effectively generates feasible, plausible, and diverse counterfactuals while offering valuable FA insights. By identifying influential features and validating their impact, GradCFA advances AI interpretability. The code for implementation of this work can be found at: https://github.com/jacob-ws/GradCFs .

Related papers

• Applied Explainability for Large Language Models: A Comparative Study [0.0]
  This paper presents an applied comparative study of three explainability techniques: Integrated Gradients, Attention Rollout, and SHAP.<n>The results show that gradient-based attribution provides more stable and intuitive explanations.<n>Work highlights key trade-offs between explainability methods and emphasizes their role as diagnostic tools rather than definitive explanations.
  arXiv  Detail & Related papers  (2026-04-15T13:07:29Z)
• Function Based Isolation Forest (FuBIF): A Unifying Framework for Interpretable Isolation-Based Anomaly Detection [46.53690373860206]
  Anomaly Detection (AD) is evolving through algorithms capable of identifying outliers in complex datasets.<n>This paper introduces the Isolation Forest (FuBIF), a generalization of IF that enables the use of real-valued functions for dataset branching.
  arXiv  Detail & Related papers  (2025-11-08T15:52:35Z)
• Reliable and Reproducible Demographic Inference for Fairness in Face Analysis [63.46525489354455]
  We propose a fully reproducible DAI pipeline that replaces conventional end-to-end training with a modular transfer learning approach.<n>We audit this pipeline across three dimensions: accuracy, fairness, and a newly introduced notion of robustness, defined via intra-identity consistency.<n>Our results show that the proposed method outperforms strong baselines, particularly on ethnicity, which is the more challenging attribute.
  arXiv  Detail & Related papers  (2025-10-23T12:22:02Z)
• Beyond Softmax: A Natural Parameterization for Categorical Random Variables [61.709831225296305]
  We introduce the $textitcatnat$ function, a function composed of a sequence of hierarchical binary splits.<n>A rich set of experiments show that the proposed function improves the learning efficiency and yields models characterized by consistently higher test performance.
  arXiv  Detail & Related papers  (2025-09-29T12:55:50Z)
• AFABench: A Generic Framework for Benchmarking Active Feature Acquisition [6.922744987645169]
  We introduce AFABench, the first benchmark framework for Active Feature Acquisition.<n>We implement and evaluate representative algorithms from all major categories, including static, greedy, and reinforcement learning-based approaches.<n>Our results highlight key trade-offs between different AFA strategies and provide actionable insights for future research.
  arXiv  Detail & Related papers  (2025-08-20T14:29:16Z)
• Trans-XFed: An Explainable Federated Learning for Supply Chain Credit Assessment [4.475469482534038]
  This paper proposes a Trans-XFed architecture that combines federated learning with explainable AI techniques for supply chain credit assessment.<n>The proposed model aims to address several key challenges, including privacy, information silos, class imbalance, non-identically and independently distributed (Non-IID) data, and model interpretability in supply chain credit assessment.
  arXiv  Detail & Related papers  (2025-08-19T10:20:57Z)
• Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why [50.191655141020505]
  This survey provides a comparative analysis of feature-based and GAN-based approaches to learning from demonstrations.<n>We argue that the dichotomy between feature-based and GAN-based methods is increasingly nuanced.
  arXiv  Detail & Related papers  (2025-07-08T11:45:51Z)
• ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability [10.957111899739926]
  Existing frameworks, such as InterpretDL and OmniXAI, integrate multiple attribution methods but suffer from scalability limitations, high coupling, theoretical constraints, and lack of user-friendly implementations.<n>We propose Attribution-Based Explainability (ABE), a unified framework that formalizes Fundamental Attribution Methods and integrates state-of-the-art attribution algorithms.
  arXiv  Detail & Related papers  (2025-05-03T12:00:59Z)
• Learning Fair Classifiers via Min-Max F-divergence Regularization [13.81078324883519]
  We introduce a novel min-max F-divergence regularization framework for learning fair classification models. We show that F-divergence measures possess convexity and differentiability properties. We show that the proposed framework achieves state-of-the-art performance with respect to the trade-off between accuracy and fairness.
  arXiv  Detail & Related papers  (2023-06-28T20:42:04Z)
• Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient [65.08966446962845]
  offline reinforcement learning, which aims at optimizing decision-making strategies with historical data, has been extensively applied in real-life applications. We take a step by considering offline reinforcement learning with differentiable function class approximation (DFA) Most importantly, we show offline differentiable function approximation is provably efficient by analyzing the pessimistic fitted Q-learning algorithm.
  arXiv  Detail & Related papers  (2022-10-03T07:59:42Z)
• MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation [132.77005365032468]
  We propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE) In our MACE approach, we propose a novel RL-based method for finding good counterfactual examples and a gradient-less descent method for improving proximity. Experiments on public datasets validate the effectiveness with better validity, sparsity and proximity.
  arXiv  Detail & Related papers  (2022-05-31T04:57:06Z)

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.