A Novel Objective Function for Counterfactual Explanations Using Conic Optimization
Bibliographic record
Abstract
Counterfactual explanations are an effective method of explaining the decisions made by machine learning models to end-users. However, it is crucial to ensure that certain qualities of counterfactuals such as plausibility and proximity are achieved, so that the explanations are realistic and effective in the real-world. In this paper, we propose a novel objective function for counterfactual explanation generation, which combines two different distance functions in the feature space and solve it using quasi-convex optimization. We compare the proposed method with three numerical optimization-based approaches on three real-world benchmark datasets. The results show that the proposed method efficiently generates c ounterfactual explanations with minimal deviation from the original samples. We evaluate the objective function on both simple models, such as logistic regression, and more complex fully connected neural networks, demonstrating its flexibility with respect to t he underlying predictive model. Moreover, the proposed method achieves stronger performance on neural network models compared with existing optimization-based approaches, providing an efficient numerical framework for counterfactual generation in neural network settings.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".