Scaling Time Series Classification via XAI-Driven Data Reduction

• URL: http://arxiv.org/abs/2607.15774v2
• Date: Wed, 22 Jul 2026 11:50:29 GMT
• Title: Scaling Time Series Classification via XAI-Driven Data Reduction
• Abstract summary: drXAI is a novel methodology that repurposes XAI attribution methods for effective data reduction in Time Series Classification.<n>Our results show the benefits of using XAI not just for interpretability, but as a robust tool for feature selection and scalability in time series analysis.
• Score: 1.6822770693792821
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Explainable AI (XAI) for time series has seen significant algorithmic growth, but its utility in providing measurable performance gains for downstream tasks remains under-explored. This paper bridges this gap by introducing drXAI, a novel methodology that repurposes XAI attribution methods for effective data reduction in Time Series Classification (TSC). The core challenge in modern TSC is scalability; state-of-the-art models, such as Transformers, exhibit quadratic complexity relative to sequence length and linear complexity relative to the number of channels. This renders them computationally prohibitive for massive datasets. drXAI addresses this by using a fast, GPU-accelerated classifier (Hydra) to generate local attributions. We aggregate these into global feature importance scores and employ an automated elbow-cut heuristic to select the most salient features without requiring manual thresholds. We evaluate our approach on both synthetic and real-world univariate and multivariate datasets. On synthetic benchmarks, drXAI successfully recovers ground-truth features where traditional baselines fail. On real-world data, drXAI achieves between 80% and 90% data reduction while maintaining classification accuracy comparable to models trained on the full dataset. Most importantly, we show that drXAI allows resource-intensive models like ConvTran to scale to datasets that were previously inaccessible due to memory constraints. Our results show the benefits of using XAI not just for interpretability, but as a robust tool for feature selection and scalability in time series analysis. All our code and data are openly available.

Related papers

• Bar-JEPA: Extracting Values from Bar Chart with Joint-Embedding Predictive Architecture [50.95839069602553]
  Bar charts are commonly used in data visualization, and while they are easily understood by humans, it is non-trivial to extract the underlying data.<n>We present a per-bar, numerical value recovery pipeline for bar charts, where a JEPA encoder is used to produce semantically rich latent features.<n>The effectiveness of self-supervised finetuning and quality of the extracted features is evident when comparing our model to end-to-end supervised baselines.
  arXiv  Detail & Related papers  (2026-08-06T14:07:26Z)
• DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams [48.434767119224375]
  We propose a paradigm shift towards Agentic Data Tailoring.<n>To overcome the data scarcity bottleneck in training such high-order capabilities, we design a two-stage pipeline.<n>$textDataClaw_0$-9B model synergizes Supervised Fine-Tuning with Group Relative Policy Optimization.
  arXiv  Detail & Related papers  (2026-06-19T11:31:43Z)
• A Sobering Look at Tabular Data Generation via Probabilistic Circuits [20.66441498486505]
  Tabular data is more challenging to generate than text and images.<n>Diffusion-based models are the current state-of-the-art (SotA) model class.<n>Deep probabilistic circuits (PCs) deliver competitive or superior performance to SotA models for a fraction of the cost.
  arXiv  Detail & Related papers  (2026-03-24T10:01:28Z)
• Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data [53.040873127309766]
  We propose a token disentanglement process within the transformer architecture, enhancing feature separation and ensuring more effective learning.<n>Our method outperforms existing models on both in-dataset and cross-dataset evaluations.
  arXiv  Detail & Related papers  (2025-09-08T17:58:06Z)
• TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation [50.23504065567638]
  This paper introduces textbfTD3, a novel textbfDataset textbfDistillation method within a meta-learning framework.<n> TD3 distills a fully expressive emphsynthetic sequence summary from original data.<n>An augmentation technique allows the learner to closely fit the synthetic summary, ensuring an accurate update of it in the emphouter-loop.
  arXiv  Detail & Related papers  (2025-02-05T03:13:25Z)
• Context Matters: Query-aware Dynamic Long Sequence Modeling of Gigapixel Images [4.3565203412433195]
  Whole slide image (WSI) analysis presents significant computational challenges due to the massive number of patches in gigapixel images.<n>We propose Querent, i.e., the query-aware long contextual dynamic modeling framework.<n>Our approach dramatically reduces computational overhead while preserving global perception to model fine-grained patch correlations.
  arXiv  Detail & Related papers  (2025-01-31T09:29:21Z)
• Classification of Raw MEG/EEG Data with Detach-Rocket Ensemble: An Improved ROCKET Algorithm for Multivariate Time Series Analysis [0.0]
  We present a novel ROCKET-based algorithm, named Detach-Rocket Ensemble, specifically designed to deal with high-dimensional data such as EEG and MEG. Our algorithm leverages pruning to provide an integrated estimation of channel importance, and ensembles to achieve better accuracy and provide a label probability. We show that Detach-Rocket Ensemble is able to provide both interpretable channel relevance and competitive classification accuracy, even when applied directly to the raw brain data.
  arXiv  Detail & Related papers  (2024-08-05T18:24:09Z)
• RU-AI: A Large Multimodal Dataset for Machine-Generated Content Detection [11.265512559447986]
  We introduce RU-AI, a new large-scale multimodal dataset for robust and effective detection of machine-generated content in text, image and voice.<n>Our dataset is constructed on the basis of three large publicly available datasets: Flickr8K, COCO and Places205.<n>The results reveal that existing models still struggle to achieve accurate and robust detection on our dataset.
  arXiv  Detail & Related papers  (2024-06-07T12:58:14Z)
• Time Series Representation Models [2.724184832774005]
  Time series analysis remains a major challenge due to its sparse characteristics, high dimensionality, and inconsistent data quality. Recent advancements in transformer-based techniques have enhanced capabilities in forecasting and imputation. We propose a new architectural concept for time series analysis based on introspection.
  arXiv  Detail & Related papers  (2024-05-28T13:25:31Z)
• MADS: Modulated Auto-Decoding SIREN for time series imputation [9.673093148930874]
  We propose MADS, a novel auto-decoding framework for time series imputation, built upon implicit neural representations. We evaluate our model on two real-world datasets, and show that it outperforms state-of-the-art methods for time series imputation.
  arXiv  Detail & Related papers  (2023-07-03T09:08:47Z)
• Optimizing Explanations by Network Canonization and Hyperparameter Search [74.76732413972005]
  Rule-based and modified backpropagation XAI approaches often face challenges when being applied to modern model architectures. Model canonization is the process of re-structuring the model to disregard problematic components without changing the underlying function. In this work, we propose canonizations for currently relevant model blocks applicable to popular deep neural network architectures.
  arXiv  Detail & Related papers  (2022-11-30T17:17:55Z)
• Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition [88.34182299496074]
  Action labels are only available on a source dataset, but unavailable on a target dataset in the training stage. We utilize a self-supervision scheme to reduce the domain shift between two skeleton-based action datasets. By segmenting and permuting temporal segments or human body parts, we design two self-supervised learning classification tasks.
  arXiv  Detail & Related papers  (2022-07-17T07:05:39Z)

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.