From SHAP to Rules: Distilling Expert Knowledge from Post-hoc Model Explanations in Time Series Classification

• URL: http://arxiv.org/abs/2508.01687v1
• Date: Sun, 03 Aug 2025 09:45:40 GMT
• Title: From SHAP to Rules: Distilling Expert Knowledge from Post-hoc Model Explanations in Time Series Classification
• Authors: Maciej Mozolewski, Szymon Bobek, Grzegorz J. Nalepa,
• Abstract summary: We propose a framework that converts numeric feature attributions from post-hoc, instance-wise explainers into structured, human-readable rules.<n>Our approach performs comparably to native rule-based methods like Anchor while scaling better to long TS and covering more instances.<n> Experiments on UCI datasets confirm that the resulting rule-based representations improve interpretability, decision transparency, and practical applicability for TS classification.
• Score: 7.7491252992917445
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Explaining machine learning (ML) models for time series (TS) classification is challenging due to inherent difficulty in raw time series interpretation and doubled down by the high dimensionality. We propose a framework that converts numeric feature attributions from post-hoc, instance-wise explainers (e.g., LIME, SHAP) into structured, human-readable rules. These rules define intervals indicating when and where they apply, improving transparency. Our approach performs comparably to native rule-based methods like Anchor while scaling better to long TS and covering more instances. Rule fusion integrates rule sets through methods such as weighted selection and lasso-based refinement to balance coverage, confidence, and simplicity, ensuring all instances receive an unambiguous, metric-optimized rule. It enhances explanations even for a single explainer. We introduce visualization techniques to manage specificity-generalization trade-offs. By aligning with expert-system principles, our framework consolidates conflicting or overlapping explanations - often resulting from the Rashomon effect - into coherent and domain-adaptable insights. Experiments on UCI datasets confirm that the resulting rule-based representations improve interpretability, decision transparency, and practical applicability for TS classification.

Related papers

• Feedback Guidance of Diffusion Models [0.0]
  Interval-Free Guidance (CFG) has become standard for improving sample fidelity in conditional diffusion models.<n>We propose FeedBack Guidance (FBG), which uses a state-dependent coefficient to self-regulate guidance amounts based on need.
  arXiv  Detail & Related papers  (2025-06-06T13:46:32Z)
• Explainability-Driven Quality Assessment for Rule-Based Systems [0.7303392100830282]
  This paper introduces an explanation framework designed to enhance the quality of rules in knowledge-based reasoning systems.<n>It generates explanations of rule inferences and leverages human interpretation to refine rules.<n>Its practicality is demonstrated through a use case in finance.
  arXiv  Detail & Related papers  (2025-02-03T11:26:09Z)
• RuleExplorer: A Scalable Matrix Visualization for Understanding Tree Ensemble Classifiers [20.416696003269674]
  This paper introduces a scalable visual analysis method to explain tree ensemble classifiers that contain tens of thousands of rules.<n>We develop an anomaly-biased model reduction method to prioritize these rules at each hierarchical level.<n>Our method fosters a deeper understanding of both common and anomalous rules, thereby enhancing interpretability without sacrificing comprehensiveness.
  arXiv  Detail & Related papers  (2024-09-05T01:48:11Z)
• Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction [75.25114727856861]
  Large language models (LLMs) tend to suffer from deterioration at the latter stage ofSupervised fine-tuning process. We introduce a simple disperse-then-merge framework to address the issue. Our framework outperforms various sophisticated methods such as data curation and training regularization on a series of standard knowledge and reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-05-22T08:18:19Z)
• Rule By Example: Harnessing Logical Rules for Explainable Hate Speech Detection [13.772240348963303]
  Rule By Example (RBE) is a novel-based contrastive learning approach for learning from logical rules for the task of textual content moderation. RBE is capable of providing rule-grounded predictions, allowing for more explainable and customizable predictions compared to typical deep learning-based approaches.
  arXiv  Detail & Related papers  (2023-07-24T16:55:37Z)
• Self-regulating Prompts: Foundational Model Adaptation without Forgetting [112.66832145320434]
  We introduce a self-regularization framework for prompting called PromptSRC. PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations.
  arXiv  Detail & Related papers  (2023-07-13T17:59:35Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning [53.68371566336254]
  We argue that the key to better performance lies in meaningful latent modality structures instead of perfect modality alignment. Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization.
  arXiv  Detail & Related papers  (2023-03-10T14:38:49Z)
• An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization [52.44068740462729]
  We present an information-theoretic perspective on the VICReg objective. We derive a generalization bound for VICReg, revealing its inherent advantages for downstream tasks. We introduce a family of SSL methods derived from information-theoretic principles that outperform existing SSL techniques.
  arXiv  Detail & Related papers  (2023-03-01T16:36:25Z)
• InteL-VAEs: Adding Inductive Biases to Variational Auto-Encoders via Intermediary Latents [60.785317191131284]
  We introduce a simple and effective method for learning VAEs with controllable biases by using an intermediary set of latent variables. In particular, it allows us to impose desired properties like sparsity or clustering on learned representations. We show that this, in turn, allows InteL-VAEs to learn both better generative models and representations.
  arXiv  Detail & Related papers  (2021-06-25T16:34:05Z)
• Towards Learning Instantiated Logical Rules from Knowledge Graphs [20.251630903853016]
  We present GPFL, a probabilistic learner rule optimized to mine instantiated first-order logic rules from knowledge graphs. GPFL utilizes a novel two-stage rule generation mechanism that first generalizes extracted paths into templates that are acyclic abstract rules. We reveal the presence of overfitting rules, their impact on the predictive performance, and the effectiveness of a simple validation method filtering out overfitting rules.
  arXiv  Detail & Related papers  (2020-03-13T00:32:46Z)

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.