SHAP Distance: An Explainability-Aware Metric for Evaluating the Semantic Fidelity of Synthetic Tabular Data

Documenti analoghi

• Critical Challenges and Guidelines in Evaluating Synthetic Tabular Data: A Systematic Review
  di: Nafis, Nazia, et al.
  Pubblicazione: (2025)
• FairSHAP: Preprocessing for Fairness Through Attribution-Based Data Augmentation
  di: Zhu, Lin, et al.
  Pubblicazione: (2025)
• Breast Cancer Classification Using Gradient Boosting Algorithms Focusing on Reducing the False Negative and SHAP for Explainability
  di: Pinheiro, João Manoel Herrera, et al.
  Pubblicazione: (2024)
• TABCF: Counterfactual Explanations for Tabular Data Using a Transformer-Based VAE
  di: Panagiotou, Emmanouil, et al.
  Pubblicazione: (2024)
• Opportunities and Challenges of Frontier Data Governance With Synthetic Data
  di: Thakur, Madhavendra, et al.
  Pubblicazione: (2025)