mlsanityData to 7 Oct 2026

xGEMs: Generating Examplars to Explain Black-Box Models

arXiv 1806.08867 ↗First posted 22 Jun 2018cs.LG stat.MLcited by 21

Not on the map. Why?

Abstract (arXiv)

This work proposes xGEMs or manifold guided exemplars, a framework to understand black-box classifier behavior by exploring the landscape of the underlying data manifold as data points cross decision boundaries. To do so, we train an unsupervised implicit generative model -- treated as a proxy to the data manifold. We summarize black-box model behavior quantitatively by perturbing data samples along the manifold. We demonstrate xGEMs' ability to detect and quantify bias in model learning and also for understanding the changes in model behavior as training progresses.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 5; 2023: 5; 2024: 2.

21 papers.

Sort:

By area:

  1. 2021Towards a Science of Human-AI Decision Making: A Survey of Empirical Studiescited by 85
  2. 2022Diffusion Models for Counterfactual Explanationscited by 79
  3. 2021Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanationscited by 56
  4. 2023Adversarial Counterfactual Visual Explanationscited by 47
  5. 2023Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generationcited by 41
  6. 2022Cycle-Consistent Counterfactuals by Latent Transformationscited by 33
  7. 2021Robust Feature-Level Adversaries are Interpretability Toolscited by 27
  8. 2021Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimatescited by 19
  9. 2021Model-Based Counterfactual Synthesizer for Interpretationcited by 14
  10. 2023Efficient XAI Techniques: A Taxonomic Surveycited by 14
  11. 2021Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbationcited by 11
  12. 2023Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactualscited by 10
9 more
  1. 2022FASTER-CE: Fast, Sparse, Transparent, and Robust Counterfactual Explanationscited by 6
  2. 2022Diagnostics for Deep Neural Networks with Automated Copy/Paste Attackscited by 6
  3. 2021δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimatescited by 4
  4. 2021Gifsplanation via Latent Shift: A Simple Autoencoder Approach to Counterfactual Generation for Chest X-rayscited by 2
  5. 2022Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Spacecited by 2
  6. 2021Explaining the Black-box Smoothly- A Counterfactual Approachcited by 1
  7. 2023Identifying Spurious Correlations using Counterfactual Alignmentcited by 1
  8. 2024Attri-Net: A Globally and Locally Inherently Interpretable Model for Multi-Label Classification Using Class-Specific Counterfactualscited by 1
  9. 2024Comparison of Machine Learning Classification Algorithms and Application to the Framingham Heart Studycited by 0