Feasible and Desirable Counterfactual Generation by Preserving Human Defined Constraints

• URL: http://arxiv.org/abs/2210.05993v1
• Date: Wed, 12 Oct 2022 08:04:37 GMT
• Title: Feasible and Desirable Counterfactual Generation by Preserving Human Defined Constraints
• Abstract summary: We present a human-in-the-loop approach to generate counterfactual (CF) explanations that preserve global and local feasibility constraints. Our approach efficiently employs this knowledge to generate CF explanation by rejecting gradient steps that violate these constraints. We demonstrate that incorporating causal constraints during CF generation results in significantly better explanations in terms of feasibility and desirability for participants.
• Score: 6.123324869194193
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a human-in-the-loop approach to generate counterfactual (CF) explanations that preserve global and local feasibility constraints. Global feasibility constraints refer to the causal constraints that are necessary for generating actionable CF explanation. Assuming a domain expert with knowledge on unary and binary causal constraints, our approach efficiently employs this knowledge to generate CF explanation by rejecting gradient steps that violate these constraints. Local feasibility constraints encode end-user's constraints for generating desirable CF explanation. We extract these constraints from the end-user of the model and exploit them during CF generation via user-defined distance metric. Through user studies, we demonstrate that incorporating causal constraints during CF generation results in significantly better explanations in terms of feasibility and desirability for participants. Adopting local and global feasibility constraints simultaneously, although improves user satisfaction, does not significantly improve desirability of the participants compared to only incorporating global constraints.

Related papers

• Generative Optimization for Incentivized Advertising with Global Level Constraints [22.46351828626369]
  GOAL is a constraint-aware generative framework that formulates incentive allocation as a conditional sequence generation problem.<n>We show that GOAL improves long-term revenue and user retention while substantially reducing ROI violation rates compared to strong baselines.
  arXiv  Detail & Related papers  (2026-08-05T04:04:07Z)
• Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models [52.87406450655783]
  Large Reasoning Models (LRMs) have demonstrated impressive capabilities in many tasks, yet they struggle with reliably following multiple instructions.<n>We formalize this challenge as the Constraint Adherence Problem (CAP)<n>This paper introduces a novel framework that addresses CAP by representing instructions as a structured knowledge graph of constraints.
  arXiv  Detail & Related papers  (2026-06-02T13:23:28Z)
• Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning [52.03884701766989]
  offline reinforcement learning (RL) algorithms typically impose constraints on action selection.<n>We propose a new neighborhood constraint that restricts action selection in the Bellman target to the union of neighborhoods of dataset actions.<n>We develop a simple yet effective algorithm, Adaptive Neighborhood-constrained Q learning (ANQ), to perform Q learning with target actions satisfying this constraint.
  arXiv  Detail & Related papers  (2025-11-04T13:42:05Z)
• Foundation Models for Logistics: Toward Certifiable, Conversational Planning Interfaces [59.80143393787701]
  Large language models (LLMs) can handle uncertainty and promise to accelerate replanning while lowering the barrier to entry.<n>We introduce a neurosymbolic framework that pairs the accessibility of natural-language dialogue with verifiable guarantees on goal interpretation.<n>A lightweight model, fine-tuned on just 100 uncertainty-filtered examples, surpasses the zero-shot performance of GPT-4.1 while cutting inference latency by nearly 50%.
  arXiv  Detail & Related papers  (2025-07-15T14:24:01Z)
• DiCoFlex: Model-agnostic diverse counterfactuals with flexible control [0.0]
  We propose DiCoFlex, a model-agnostic, conditional generative framework that produces multiple diverse counterfactuals in a single forward pass.<n>We show that DiCoFlex outperforms existing methods in terms of validity, diversity, proximity, and constraint adherence.
  arXiv  Detail & Related papers  (2025-05-29T17:37:47Z)
• DiCE-Extended: A Robust Approach to Counterfactual Explanations in Machine Learning [0.0]
  Counterfactual explanations are a key approach in Explainable artificial intelligence (XAI) Existing generation methods often struggle to balance proximity, diversity, and robustness, limiting their real-world applicability. A widely adopted framework, Diverse Counterfactual Explanations (DiCE), emphasizes diversity but lacks robustness, making CF explanations sensitive to perturbations and domain constraints. We introduce DiCE-Extended, an enhanced CF explanation framework that integrates multi-objective optimization techniques to improve robustness while maintaining interpretability.
  arXiv  Detail & Related papers  (2025-04-26T21:22:44Z)
• CP-NCBF: A Conformal Prediction-based Approach to Synthesize Verified Neural Control Barrier Functions [2.092779643426281]
  Control Barrier Functions (CBFs) are a practical approach for designing safety-critical controllers. Recent efforts have explored learning-based methods, such as neural CBFs, to address this issue. We propose a novel framework that leverages split-conformal prediction to generate formally verified neural CBFs.
  arXiv  Detail & Related papers  (2025-03-18T10:01:06Z)
• Constrained Language Generation with Discrete Diffusion Models [61.81569616239755]
  We present Constrained Discrete Diffusion (CDD), a novel method for enforcing constraints on natural language by integrating discrete diffusion models with differentiable optimization. We show how this technique can be applied to satisfy a variety of natural language constraints, including (i) toxicity mitigation by preventing harmful content from emerging, (ii) character and sequence level lexical constraints, and (iii) novel molecule sequence generation with specific property adherence.
  arXiv  Detail & Related papers  (2025-03-12T19:48:12Z)
• Flexible Counterfactual Explanations with Generative Models [1.3499500088995464]
  We introduce Flexible Counterfactual Explanations, a framework incorporating counterfactual templates. FCEGAN align explanations with user-defined constraints without requiring model retraining or additional optimization. Experiments across economic and healthcare datasets demonstrate that FCEGAN significantly improves counterfactual explanations' validity.
  arXiv  Detail & Related papers  (2025-02-24T20:01:04Z)
• Diffusion Predictive Control with Constraints [51.91057765703533]
  Diffusion predictive control with constraints (DPCC) An algorithm for diffusion-based control with explicit state and action constraints that can deviate from those in the training data. We show through simulations of a robot manipulator that DPCC outperforms existing methods in satisfying novel test-time constraints while maintaining performance on the learned control task.
  arXiv  Detail & Related papers  (2024-12-12T15:10:22Z)
• Deep Neural Network for Constraint Acquisition through Tailored Loss Function [0.0]
  The significance of learning constraints from data is underscored by its potential applications in real-world problem-solving. This work introduces a novel approach grounded in Deep Neural Network (DNN) based on Symbolic Regression.
  arXiv  Detail & Related papers  (2024-03-04T13:47:33Z)
• Introducing User Feedback-based Counterfactual Explanations (UFCE) [49.1574468325115]
  Counterfactual explanations (CEs) have emerged as a viable solution for generating comprehensible explanations in XAI. UFCE allows for the inclusion of user constraints to determine the smallest modifications in the subset of actionable features. UFCE outperforms two well-known CE methods in terms of textitproximity, textitsparsity, and textitfeasibility.
  arXiv  Detail & Related papers  (2024-02-26T20:09:44Z)
• Achieving Constraints in Neural Networks: A Stochastic Augmented Lagrangian Approach [49.1574468325115]
  Regularizing Deep Neural Networks (DNNs) is essential for improving generalizability and preventing overfitting. We propose a novel approach to DNN regularization by framing the training process as a constrained optimization problem. We employ the Augmented Lagrangian (SAL) method to achieve a more flexible and efficient regularization mechanism.
  arXiv  Detail & Related papers  (2023-10-25T13:55:35Z)
• Safe Neural Control for Non-Affine Control Systems with Differentiable Control Barrier Functions [58.19198103790931]
  This paper addresses the problem of safety-critical control for non-affine control systems. It has been shown that optimizing quadratic costs subject to state and control constraints can be sub-optimally reduced to a sequence of quadratic programs (QPs) by using Control Barrier Functions (CBFs) We incorporate higher-order CBFs into neural ordinary differential equation-based learning models as differentiable CBFs to guarantee safety for non-affine control systems.
  arXiv  Detail & Related papers  (2023-09-06T05:35:48Z)
• Compositional Diffusion-Based Continuous Constraint Solvers [98.1702285470628]
  This paper introduces an approach for learning to solve continuous constraint satisfaction problems (CCSP) in robotic reasoning and planning. By contrast, our model, the compositional diffusion continuous constraint solver (Diffusion-CCSP), derives global solutions to CCSPs.
  arXiv  Detail & Related papers  (2023-09-02T15:20:36Z)
• Computational-level Analysis of Constraint Compliance for General Intelligence [4.383011485317949]
  Rules, manners' laws, and moral imperatives are examples of classes of constraints that govern human behavior. Despite such messiness, humans incorporate constraints in their decisions robustly and rapidly. General, artificially-intelligent agents must also be able to navigate the messiness of systems of real-world constraints.
  arXiv  Detail & Related papers  (2023-03-08T03:25:24Z)
• Optimal Decision Trees For Interpretable Clustering with Constraints (Extended Version) [7.799182201815762]
  Constrained clustering is a semi-supervised task that employs a limited amount of labelled data, formulated as constraints. We present a novel SAT-based framework for interpretable clustering that supports clustering constraints. We also present new insight into the trade-off between interpretability and satisfaction of such user-provided constraints.
  arXiv  Detail & Related papers  (2023-01-30T05:34:49Z)
• Finding Counterfactual Explanations through Constraint Relaxations [6.961253535504979]
  Interactive constraint systems often suffer from infeasibility (no solution) due to conflicting user constraints. A common approach to recover infeasibility is to eliminate the constraints that cause the conflicts in the system. We propose an iterative method based on conflict detection and maximal relaxations in over-constrained constraint satisfaction problems.
  arXiv  Detail & Related papers  (2022-04-07T13:18:54Z)
• Controllable Summarization with Constrained Markov Decision Process [50.04321779376415]
  We study controllable text summarization which allows users to gain control on a particular attribute. We propose a novel training framework based on Constrained Markov Decision Process (CMDP) Our framework can be applied to control important attributes of summarization, including length, covered entities, and abstractiveness.
  arXiv  Detail & Related papers  (2021-08-07T09:12:53Z)
• Pointwise Feasibility of Gaussian Process-based Safety-Critical Control under Model Uncertainty [77.18483084440182]
  Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs) are popular tools for enforcing safety and stability of a controlled system, respectively. We present a Gaussian Process (GP)-based approach to tackle the problem of model uncertainty in safety-critical controllers that use CBFs and CLFs.
  arXiv  Detail & Related papers  (2021-06-13T23:08:49Z)
• Satisfiability and Query Answering in Description Logics with Global and Local Cardinality Constraints [6.961253535504978]
  We introduce and investigate the expressive description logic (DL) ALCSCC++, in which the global and local cardinality constraints can be mixed. On the one hand, we prove that this does not increase the complexity of satisfiability checking and other standard inference problems. On the other hand, the satisfiability problem becomes undecidable if inverse roles are added to the languages.
  arXiv  Detail & Related papers  (2020-02-14T15:28:15Z)

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.