Cover Image

Mechanistic Interpretability for Transformer-based Time Series Classification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kalnāre, Matīss, Kitharidis, Sofoklis, Bäck, Thomas, van Stein, Niki
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TX-Gen: Multi-Objective Optimization for Sparse Counterfactual Explanations for Time-Series Classification
by: Huang, Qi, et al.
Published: (2024)

Visual Model Selection using Feature Importance Clusters in Fairness-Performance Similarity Optimized Space
by: Kitharidis, Sofoklis, et al.
Published: (2025)

Shapelet-based Model-agnostic Counterfactual Local Explanations for Time Series Classification
by: Huang, Qi, et al.
Published: (2024)

Multi-Step Reasoning with Large Language Models, a Survey
by: Plaat, Aske, et al.
Published: (2024)

Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
by: Yıldırım, Alper
Published: (2026)

Evaluating Simplification Algorithms for Interpretability of Time Series Classification
by: Håvardstun, Brigt, et al.
Published: (2025)

CRITS: Convolutional Rectifier for Interpretable Time Series Classification
by: Kuratomi, Alejandro, et al.
Published: (2025)

ST-Tree with Interpretability for Multivariate Time Series Classification
by: Du, Mingsen, et al.
Published: (2024)

Diffusion and Flow Matching Models for Tabular Data: A Survey
by: Li, Zhong, et al.
Published: (2025)

nnterp: A Standardized Interface for Mechanistic Interpretability of Transformers
by: Dumas, Clément
Published: (2025)

Inherently Interpretable Time Series Classification via Multiple Instance Learning
by: Early, Joseph, et al.
Published: (2023)

Benchmarking Counterfactual Interpretability in Deep Learning Models for Time Series Classification
by: Kan, Ziwen, et al.
Published: (2024)

Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs
by: El, Batu, et al.
Published: (2025)

EDformer: Embedded Decomposition Transformer for Interpretable Multivariate Time Series Predictions
by: Chakraborty, Sanjay, et al.
Published: (2024)

ShapeFormer: Shapelet Transformer for Multivariate Time Series Classification
by: Le, Xuan-May, et al.
Published: (2024)

What-If Explanations Over Time: Counterfactuals for Time Series Classification
by: Schlegel, Udo, et al.
Published: (2026)

LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics
by: van Stein, Niki, et al.
Published: (2024)

Transforming Multidimensional Time Series into Interpretable Event Sequences for Advanced Data Mining
by: Yan, Xu, et al.
Published: (2024)

Why Are You Wrong? Counterfactual Explanations for Language Grounding with 3D Objects
by: Preintner, Tobias, et al.
Published: (2025)

Interpretable Pre-Trained Transformers for Heart Time-Series Data
by: Davies, Harry J., et al.
Published: (2024)

Gradient-based Model Shortcut Detection for Time Series Classification
by: Ibarra, Salomon, et al.
Published: (2025)

PHEATPRUNER: Interpretable Data-centric Feature Selection for Multivariate Time Series Classification through Persistent Homology
by: Pham, Anh-Duy, et al.
Published: (2025)

Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series
by: Song, Xianhao, et al.
Published: (2026)

Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification
by: Kermani, Arshia, et al.
Published: (2025)

Challenges in Mechanistically Interpreting Model Representations
by: Golechha, Satvik, et al.
Published: (2024)

Interpretable Time Series Autoregression for Periodicity Quantification
by: Chen, Xinyu, et al.
Published: (2025)

Correlating Time Series with Interpretable Convolutional Kernels
by: Chen, Xinyu, et al.
Published: (2024)

Online Model-based Anomaly Detection in Multivariate Time Series: Taxonomy, Survey, Research Challenges and Future Directions
by: Correia, Lucas, et al.
Published: (2024)

Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
by: Winninger, Thomas, et al.
Published: (2025)

A Survey of Transformer Enabled Time Series Synthesis
by: Sommers, Alexander, et al.
Published: (2024)

Automated Algorithm Design for Auto-Tuning Optimizers
by: Willemsen, Floris-Jan, et al.
Published: (2025)

MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning
by: He, Jesse, et al.
Published: (2026)

Semi-Periodic Activation for Time Series Classification
by: Júnior, José Gilberto Barbosa de Medeiros, et al.
Published: (2024)

VSFormer: Value and Shape-Aware Transformer with Prior-Enhanced Self-Attention for Multivariate Time Series Classification
by: Xi, Wenjie, et al.
Published: (2024)

PRISM: Lightweight Multivariate Time-Series Classification through Symmetric Multi-Resolution Convolutional Layers
by: Zucchi, Federico, et al.
Published: (2025)

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
by: Chen, Xi, et al.
Published: (2025)

Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability
by: Yan, Ge, et al.
Published: (2025)

A Survey on Deep Learning based Time Series Analysis with Frequency Transformation
by: Yi, Kun, et al.
Published: (2023)

CAPS: Unifying Attention, Recurrence, and Alignment in Transformer-based Time Series Forecasting
by: Pati, Viresh, et al.
Published: (2026)

A Comparative Study of Pruning Methods in Transformer-based Time Series Forecasting
by: Kiefer, Nicholas, et al.
Published: (2024)