No $D_{\text{train}}$: Model-Agnostic Counterfactual Explanations Using Reinforcement Learning

• URL: http://arxiv.org/abs/2405.18563v2
• Date: Thu, 10 Jul 2025 17:01:15 GMT
• Title: No $D_{\text{train}}$: Model-Agnostic Counterfactual Explanations Using Reinforcement Learning
• Authors: Xiangyu Sun, Raquel Aoki, Kevin H. Wilson,
• Abstract summary: We present NTD-CFE, a model-agnostic CFE that generates CFEs when training datasets are unavailable.<n>We show that NTD-CFE finds CFEs that make significantly fewer and significantly smaller changes to the input time-series.<n>These properties make CFEs more actionable, as the magnitude of change required to alter an outcome is vastly reduced.
• Score: 4.039558709616107
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Machine learning (ML) methods have experienced significant growth in the past decade, yet their practical application in high-impact real-world domains has been hindered by their opacity. When ML methods are responsible for making critical decisions, stakeholders often require insights into how to alter these decisions. Counterfactual explanations (CFEs) have emerged as a solution, offering interpretations of opaque ML models and providing a pathway to transition from one decision to another. However, most existing CFE methods require access to the model's training dataset, few methods can handle multivariate time-series, and none of model-agnostic CFE methods can handle multivariate time-series without training datasets. These limitations can be formidable in many scenarios. In this paper, we present NTD-CFE, a novel model-agnostic CFE method based on reinforcement learning (RL) that generates CFEs when training datasets are unavailable. NTD-CFE is suitable for both static and multivariate time-series datasets with continuous and discrete features. NTD-CFE reduces the CFE search space from a multivariate time-series domain to a lower dimensional space and addresses the problem using RL. Users have the flexibility to specify non-actionable, immutable, and preferred features, as well as causal constraints. We demonstrate the performance of NTD-CFE against four baselines on several datasets and find that, despite not having access to a training dataset, NTD-CFE finds CFEs that make significantly fewer and significantly smaller changes to the input time-series. These properties make CFEs more actionable, as the magnitude of change required to alter an outcome is vastly reduced. The code is available in the supplementary material.

Related papers

• UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality [52.49062565901046]
  Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models with human values.<n>Existing approaches struggle to capture the multi-dimensional, distributional nuances of human preferences.<n>We introduce Utility-Conditioned Multi-Objective Alignment (UC-MOA), a novel framework that overcomes these limitations.
  arXiv  Detail & Related papers  (2025-03-10T09:52:42Z)
• AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting [10.899510048905926]
  We present adapters for managing intricate dependencies among features and quantifying uncertainty in predictions. Experiments conducted on both synthetic and real-world datasets confirm the efficacy of adapters. Our framework, AdaPTS, positions adapters as a modular, scalable, and effective solution.
  arXiv  Detail & Related papers  (2025-02-14T15:46:19Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Multi-SpaCE: Multi-Objective Subsequence-based Sparse Counterfactual Explanations for Multivariate Time Series Classification [3.8305310459921587]
  Multi-SpaCE balances proximity, sparsity, plausibility, and contiguity in time series data. It consistently achieves perfect validity and delivers superior performance compared to existing methods.
  arXiv  Detail & Related papers  (2024-12-14T09:21:44Z)
• Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework [58.362064122489166]
  This paper introduces the Cross-modal Few-Shot Learning task, which aims to recognize instances from multiple modalities when only a few labeled examples are available. We propose a Generative Transfer Learning framework consisting of two stages: the first involves training on abundant unimodal data, and the second focuses on transfer learning to adapt to novel data. Our finds demonstrate that GTL has superior performance compared to state-of-the-art methods across four distinct multi-modal datasets.
  arXiv  Detail & Related papers  (2024-10-14T16:09:38Z)
• A Practitioner's Guide to Continual Multimodal Pretraining [83.63894495064855]
  Multimodal foundation models serve numerous applications at the intersection of vision and language. To keep models updated, research into continual pretraining mainly explores scenarios with either infrequent, indiscriminate updates on large-scale new data, or frequent, sample-level updates. We introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements.
  arXiv  Detail & Related papers  (2024-08-26T17:59:01Z)
• Benchmarking Counterfactual Interpretability in Deep Learning Models for Time Series Classification [6.683066713491661]
  Counterfactual (CF) methods are used to identify minimal changes in instances to alter the model predictions. Despite extensive research, no existing work benchmarks CF methods in the time series domain. In this work, we redesign quantitative metrics to accurately capture desirable characteristics in CFs.
  arXiv  Detail & Related papers  (2024-08-22T18:17:26Z)
• Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond [13.867793835583463]
  We propose an uncertainty-aware memory-based approach to solve catastrophic forgetting. We retrieve samples with specific characteristics, and - by retraining the model on such samples - we demonstrate the potential of this approach.
  arXiv  Detail & Related papers  (2024-05-29T09:29:39Z)
• Learning Actionable Counterfactual Explanations in Large State Spaces [16.30292272064278]
  We introduce three recourse types grounded in real-world actions.<n>High-level continuous (emphhl-continuous), high-level discrete (emphhl-discrete), and high-level ID (emphhl-id) CFEs.
  arXiv  Detail & Related papers  (2024-04-25T20:49:03Z)
• Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning [55.715623885418815]
  Cross-Domain Few-Shot Learning methods require access to source domain data to train a model in the pre-training phase. Due to increasing concerns about data privacy and the desire to reduce data transmission and training costs, it is necessary to develop a CDFSL solution without accessing source data. This paper proposes an Enhanced Information Maximization with Distance-Aware Contrastive Learning method to address these challenges.
  arXiv  Detail & Related papers  (2024-03-04T12:10:24Z)
• FCDNet: Frequency-Guided Complementary Dependency Modeling for Multivariate Time-Series Forecasting [9.083469629116784]
  We propose FCDNet, a concise yet effective framework for time-series forecasting. It helps extract long- and short-term dependency information adaptively from multi-level frequency patterns. Experiments show that FCDNet significantly exceeds strong baselines.
  arXiv  Detail & Related papers  (2023-12-27T07:29:52Z)
• Task-Distributionally Robust Data-Free Meta-Learning [99.56612787882334]
  Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data. For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift ( TDS) and Task-Distribution Corruption (TDC)
  arXiv  Detail & Related papers  (2023-11-23T15:46:54Z)
• TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series [57.4208255711412]
  Building on copula theory, we propose a simplified objective for the recently-introduced transformer-based attentional copulas (TACTiS) We show that the resulting model has significantly better training dynamics and achieves state-of-the-art performance across diverse real-world forecasting tasks.
  arXiv  Detail & Related papers  (2023-10-02T16:45:19Z)
• Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations [56.941276017696076]
  We propose a conceptually simple yet effective solution named Counterfactual Explanations with Minimal Satisfiable Perturbations (CEMSP) CEMSP constrains changing values of abnormal features with the help of their semantically meaningful normal ranges. Compared to existing methods, we conduct comprehensive experiments on both synthetic and real-world datasets to demonstrate that our method provides more robust explanations while preserving flexibility.
  arXiv  Detail & Related papers  (2023-09-09T04:05:56Z)
• Detecting Morphing Attacks via Continual Incremental Training [10.796380524798744]
  Recent Continual Learning (CL) paradigm may represent an effective solution to enable incremental training, even through multiple sites. We investigate the performance of different Continual Learning methods in this scenario, simulating a learning model that is updated every time a new chunk of data, even of variable size, is available. Experimental results reveal that a particular CL method, namely Learning without Forgetting (LwF), is one of the best-performing algorithms.
  arXiv  Detail & Related papers  (2023-07-27T17:48:29Z)
• To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis [50.31589712761807]
  Large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its scaling limit for LLMs. We investigate the consequences of repeating pre-training data, revealing that the model is susceptible to overfitting. Second, we examine the key factors contributing to multi-epoch degradation, finding that significant factors include dataset size, model parameters, and training objectives.
  arXiv  Detail & Related papers  (2023-05-22T17:02:15Z)
• A Framework of Meta Functional Learning for Regularising Knowledge Transfer [89.74127682599898]
  This work proposes a novel framework of Meta Functional Learning (MFL) by meta-learning a generalisable functional model from data-rich tasks. The MFL computes meta-knowledge on functional regularisation generalisable to different learning tasks by which functional training on limited labelled data promotes more discriminative functions to be learned.
  arXiv  Detail & Related papers  (2022-03-28T15:24:09Z)
• Amortized Generation of Sequential Counterfactual Explanations for Black-box Models [26.91950709495675]
  Counterfactual explanations (CFEs) provide what if'' feedback of a form. Current CFE approaches are single shot -- that is, they assume $x$ can change to $x'$ in a single time period. We propose a novel approach that generates sequential CFEs that allow $x$ to move across intermediate states to a final state $x'$.
  arXiv  Detail & Related papers  (2021-06-07T20:54:48Z)
• Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning [96.75889543560497]
  In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a limited number of samples. We propose a novel training mechanism that simultaneously enforces equivariance and invariance to a general set of geometric transformations.
  arXiv  Detail & Related papers  (2021-03-01T21:14:33Z)
• FLUID: A Unified Evaluation Framework for Flexible Sequential Data [42.44973069520298]
  We introduce a new unified evaluation framework - FLUID (Flexible Sequential Data) FLUID integrates the objectives of few-shot, continual, transfer, and representation learning. We conduct experiments on a broad set of methods which shed new insight on the advantages and limitations of current solutions.
  arXiv  Detail & Related papers  (2020-07-06T04:31:54Z)

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.