ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting

• URL: http://arxiv.org/abs/2509.23159v2
• Date: Tue, 21 Oct 2025 01:37:10 GMT
• Title: ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting
• Authors: Ziheng Peng, Shijie Ren, Xinyue Gu, Linxiao Yang, Xiting Wang, Liang Sun,
• Abstract summary: We propose ProtoTS, a novel interpretable forecasting framework that achieves both high accuracy and transparent decision-making.<n>ProtoTS computes instance-prototype similarity based on a denoised representation that preserves abundant heterogeneous information.<n> Experiments on multiple realistic benchmarks, including a newly released LOF dataset, show that ProtoTS not only exceeds existing methods in forecast accuracy but also delivers expert-steerable interpretations.
• Score: 25.219624871510376
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While deep learning has achieved impressive performance in time series forecasting, it becomes increasingly crucial to understand its decision-making process for building trust in high-stakes scenarios. Existing interpretable models often provide only local and partial explanations, lacking the capability to reveal how heterogeneous and interacting input variables jointly shape the overall temporal patterns in the forecast curve. We propose ProtoTS, a novel interpretable forecasting framework that achieves both high accuracy and transparent decision-making through modeling prototypical temporal patterns. ProtoTS computes instance-prototype similarity based on a denoised representation that preserves abundant heterogeneous information. The prototypes are organized hierarchically to capture global temporal patterns with coarse prototypes while capturing finer-grained local variations with detailed prototypes, enabling expert steering and multi-level interpretability. Experiments on multiple realistic benchmarks, including a newly released LOF dataset, show that ProtoTS not only exceeds existing methods in forecast accuracy but also delivers expert-steerable interpretations for better model understanding and decision support.

Related papers

• It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks [87.7937890373758]
  Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation.<n>We introduce TIME, a next-generation task-centric benchmark comprising 50 fresh datasets and 98 forecasting tasks.<n>We propose a novel pattern-level evaluation perspective that moves beyond traditional dataset-level evaluations based on static meta labels.
  arXiv  Detail & Related papers  (2026-02-12T16:31:01Z)
• Explainable time-series forecasting with sampling-free SHAP for Transformers [3.515829683606796]
  We introduce SHAPformer, an accurate, fast and sampling-free explainable time-series forecasting model based on the Transformer architecture.<n>It generates explanations in under one second, several orders of magnitude faster than the SHAP Permutation Explainer.<n>On synthetic data with ground truth explanations, SHAPformer provides explanations that are true to the data.
  arXiv  Detail & Related papers  (2025-12-23T17:02:35Z)
• GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series [5.364986293275663]
  We present textbfGenFacts, a novel generative framework for producing plausible and actionable counterfactual explanations.<n>We evaluate GenFacts on radar gesture recognition as an industrial use case and handwritten letter trajectories as an intuitive benchmark.
  arXiv  Detail & Related papers  (2025-09-25T09:22:19Z)
• FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning [4.244188591221394]
  We propose a novel framework named Federated Learning via Semantic Anchors (FedSA) to decouple the generation of prototypes from local representation learning.<n>FedSA significantly outperforms existing prototype-based FL methods on various classification tasks.
  arXiv  Detail & Related papers  (2025-01-09T16:10:03Z)
• DCIts -- Deep Convolutional Interpreter for time series [0.0]
  The model is designed so one can robustly determine the optimal window size that captures all necessary interactions within the smallest possible time frame.<n>It effectively identifies the optimal model order, balancing complexity when incorporating higher-order terms.<n>These advancements hold significant implications for modeling and understanding dynamic systems, making the model a valuable tool for applied and computational physicists.
  arXiv  Detail & Related papers  (2025-01-08T08:21:58Z)
• Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift [51.01356105618118]
  Time series often exhibit complex non-uniform distribution with varying patterns across segments, such as season, operating condition, or semantic meaning.<n>Existing approaches, which typically train a single model to capture all these diverse patterns, often struggle with the pattern drifts between patches.<n>We propose TFPS, a novel architecture that leverages pattern-specific experts for more accurate and adaptable time series forecasting.
  arXiv  Detail & Related papers  (2024-10-13T13:35:29Z)
• Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval [139.21955930418815]
  Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts. We propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity.
  arXiv  Detail & Related papers  (2023-09-29T09:41:19Z)
• OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning [67.07363529640784]
  We propose OpenSTL to categorize prevalent approaches into recurrent-based and recurrent-free models. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow and forecasting weather. We find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models.
  arXiv  Detail & Related papers  (2023-06-20T03:02:14Z)
• ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model [18.537838366377915]
  ProtoVAE is a variational autoencoder-based framework that learns class-specific prototypes in an end-to-end manner. It enforces trustworthiness and diversity by regularizing the representation space and introducing an orthonormality constraint.
  arXiv  Detail & Related papers  (2022-10-15T00:42:13Z)
• An Additive Instance-Wise Approach to Multi-class Model Interpretation [53.87578024052922]
  Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. Existing methods mainly focus on selecting explanatory input features, which follow either locally additive or instance-wise approaches. This work exploits the strengths of both methods and proposes a global framework for learning local explanations simultaneously for multiple target classes.
  arXiv  Detail & Related papers  (2022-07-07T06:50:27Z)
• Attentional Prototype Inference for Few-Shot Segmentation [128.45753577331422]
  We propose attentional prototype inference (API), a probabilistic latent variable framework for few-shot segmentation. We define a global latent variable to represent the prototype of each object category, which we model as a probabilistic distribution. We conduct extensive experiments on four benchmarks, where our proposal obtains at least competitive and often better performance than state-of-the-art prototype-based methods.
  arXiv  Detail & Related papers  (2021-05-14T06:58:44Z)
• Feature Importance Explanations for Temporal Black-Box Models [3.655021726150369]
  We propose TIME, a method to explain models that are inherently temporal in nature. Our approach uses a model-agnostic permutation-based approach to analyze global feature importance.
  arXiv  Detail & Related papers  (2021-02-23T20:41:07Z)

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.