DISCOVER: A Solver for Distributional Counterfactual Explanations

• URL: http://arxiv.org/abs/2603.16436v1
• Date: Tue, 17 Mar 2026 12:18:27 GMT
• Title: DISCOVER: A Solver for Distributional Counterfactual Explanations
• Abstract summary: DISCOVER is a model-agnostic solver for distributional counterfactual explanations.<n>It exploits a sample-wise decomposition of the transport objective to compute per-row impact scores and enforce a top-$k$ intervention budget.<n> Experiments on multiple datasets demonstrate strong joint alignment of input and output distributions.
• Score: 7.673379790081033
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Counterfactual explanations (CE) explain model decisions by identifying input modifications that lead to different predictions. Most existing methods operate at the instance level. Distributional Counterfactual Explanations (DCE) extend this setting by optimizing an optimal transport objective that balances proximity to a factual input distribution and alignment to a target output distribution, with statistical certification via chance constrained bounds. However, DCE relies on gradient based optimization, while many real-world tabular pipelines are dominated by non-differentiable models. We propose DISCOVER, a model-agnostic solver for distributional counterfactual explanations. DISCOVER preserves the original DCE objective and certification while replacing gradient descent with a sparse propose-and-select search paradigm. It exploits a sample-wise decomposition of the transport objective to compute per-row impact scores and enforce a top-$k$ intervention budget, focusing edits on the most influential samples. To guide candidate generation without predictor gradients, DISCOVER introduces an OT-guided cone sampling primitive driven by input-side transport geometry. Experiments on multiple tabular datasets demonstrate strong joint alignment of input and output distributions, extending distributional counterfactual reasoning to modern black box learning pipelines. A code repository is available at https://github.com/understanding-ml/DCE.

Related papers

• Distribution-Alignment Bridge for Uncertainty-Aware Text-to-Video Retrieval [6.5819669635975915]
  This paper proposes a framework that reconceptualizes text-to-video retrieval as a distribution alignment task rather than traditional deterministic point matching.<n>By modeling both text and video embeddings as Gaussian distributions defined by mean and variance, DAB explicitly accounts for modality-specific uncertainty.<n>We employ a deterministic, diffusion-inspired bridge to iteratively refine text distributions toward their target video distributions through a truncated refinement process.
  arXiv  Detail & Related papers  (2026-07-23T07:07:28Z)
• TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models [4.9352098965615]
  We study how to construct valid and informative regions for multi-dimensional outputs.<n>We measure how well a candidate output aligns with the learned generative dynamics by averaging denoising velocity or errors along transport trajectories.<n>The resulting transport-based scores are scalar-valued and can be calibrated using conformal prediction split.
  arXiv  Detail & Related papers  (2026-05-08T01:28:57Z)
• Dual-Teacher Distillation with Subnetwork Rectification for Black-Box Domain Adaptation [69.7036779439312]
  Black box domain adaptation represents a highly practical yet extremely challenging setting.<n>We propose a dual teacher distillation with subnetwork rectification (DDSR) model that exploits specific knowledge embedded in black box source models.<n>Our approach demonstrates consistent improvements over state of the art methods, including those using source data or models.
  arXiv  Detail & Related papers  (2026-03-24T07:54:19Z)
• Evidence-based Distributional Alignment for Large Language Models [58.65469623911573]
  We propose Evi-DA, an evidence-based alignment technique that improves the fidelity and robustness of LLM-based distribution estimation.<n>Given a target country, Evi-DA retrieves related World Values Survey items and their answer distributions, predicts a coarse Welzel value signature for each option, and infers the country-conditioned answer distribution in a structured format.
  arXiv  Detail & Related papers  (2026-03-03T03:34:06Z)
• Learnable Chernoff Baselines for Inference-Time Alignment [64.81256817158851]
  We introduce Learnable Chernoff Baselines as a method for efficiently and approximately sampling from exponentially tilted kernels.<n>We establish total-variation guarantees to the ideal aligned model, and demonstrate in both continuous and discrete diffusion settings that LCB sampling closely matches ideal rejection sampling.
  arXiv  Detail & Related papers  (2026-02-08T00:09:40Z)
• Adapt, But Don't Forget: Fine-Tuning and Contrastive Routing for Lane Detection under Distribution Shift [3.394257279821418]
  Cross-dataset distribution shifts can cause catastrophic forgetting during fine-tuning.<n>Our framework achieves near-optimal F1-scores while using significantly fewer parameters than training separate models for each distribution.
  arXiv  Detail & Related papers  (2025-07-22T18:39:15Z)
• Distributionally Robust Coreset Selection under Covariate Shift [14.979902937312099]
  Coreset selection is an approach to reducing training data.<n>It is challenging to select an effective subset of training data that performs well across all deployment scenarios.<n>We propose Distributionally Robust Coreset Selection (DRCS) for this purpose.
  arXiv  Detail & Related papers  (2025-01-24T05:36:53Z)
• Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts [33.677249894085186]
  We explore the potential of Concept Bottleneck Models for transforming complex, non-interpretable foundation models into interpretable decision-making pipelines.<n>Specifically, we focus on the test-time deployment of such an interpretable CBM pipeline "in the wild"<n>Our adaptation method produces concept-based interpretations better aligned with the test data and boosts post-deployment accuracy by up to 28%.
  arXiv  Detail & Related papers  (2024-12-18T17:47:46Z)
• Rejection via Learning Density Ratios [50.91522897152437]
  Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions.<n>We propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance.<n>Our framework is tested empirically over clean and noisy datasets.
  arXiv  Detail & Related papers  (2024-05-29T01:32:17Z)
• Distributional Counterfactual Explanations With Optimal Transport [7.597676579494146]
  Counterfactual explanations (CE) are the de facto method for providing insights into black-box decision-making models.<n>This paper proposes distributional counterfactual explanation (DCE), shifting focus to the distributional properties of observed and counterfactual data.
  arXiv  Detail & Related papers  (2024-01-23T21:48:52Z)
• Semi-DETR: Semi-Supervised Object Detection with Detection Transformers [105.45018934087076]
  We analyze the DETR-based framework on semi-supervised object detection (SSOD) We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector. Our method outperforms all state-of-the-art methods by clear margins.
  arXiv  Detail & Related papers  (2023-07-16T16:32:14Z)
• Explaining Cross-Domain Recognition with Interpretable Deep Classifier [100.63114424262234]
  Interpretable Deep (IDC) learns the nearest source samples of a target sample as evidence upon which the classifier makes the decision. Our IDC leads to a more explainable model with almost no accuracy degradation and effectively calibrates classification for optimum reject options.
  arXiv  Detail & Related papers  (2022-11-15T15:58:56Z)

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.