Enhancing Model Explainability with CTGAN-LIME: A Novel Approach for Interpretable Machine Learning
Bibliographic record
Abstract
Machine learning (ML) has become integral in numerous industries, offering unparalleled data analysis, pattern recognition, and predictive modelling advantages.However, the opacity of ML models, often referred to as "black boxes," poses significant challenges in understanding their decision-making processes.Explainable Artificial Intelligence (XAI) techniques aim to address this challenge by providing transparency into ML models' inner workings, enhancing human comprehension and trust.This study proposes a novel approach, CTGAN-LIME, combining Conditional Tabular Generative Adversarial Networks (CTGAN) with the LIME (Local Interpretable Model-Agnostic Explanations) framework to enhance model explainability.CTGAN-LIME addresses LIME's limitations by structuring neighbourhood sample generation and considering class balance, thereby improving the reliability and stability of explanations.Empirical evaluations across diverse datasets demonstrate CTGAN-LIME's superiority in local fidelity, stability, and local concordance over traditional LIME, underscoring its effectiveness in enhancing trustworthiness across various black-box models.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".