Copertina

TimeSAE: Sparse Decoding for Faithful Explanations of Black-Box Time Series Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Oublal, Khalid, Bouniot, Quentin, Gan, Qi, Clémençon, Stephan, Akata, Zeynep
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers
di: Roschmann, Simon, et al.
Pubblicazione: (2025)

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
di: Pach, Mateusz, et al.
Pubblicazione: (2025)

SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport
di: Roschmann, Simon, et al.
Pubblicazione: (2026)

Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers
di: Huang, Yiran, et al.
Pubblicazione: (2026)

The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
di: Pach, Mateusz, et al.
Pubblicazione: (2026)

Sparse Autoencoders are Topic Models
di: Girrbach, Leander, et al.
Pubblicazione: (2025)

Time is Not Enough: Time-Frequency based Explanation for Time-Series Black-Box Models
di: Chung, Hyunseung, et al.
Pubblicazione: (2024)

Sparse and Faithful Explanations Without Sparse Models
di: Sun, Yiyang, et al.
Pubblicazione: (2024)

Flexible Parametric Inference for Space-Time Hawkes Processes
di: Siviero, Emilia, et al.
Pubblicazione: (2024)

Faithful and Interpretable Explanations for Complex Ensemble Time Series Forecasts using Surrogate Models and Forecastability Analysis
di: Zhao, Yikai, et al.
Pubblicazione: (2025)

The Manifold Hypothesis for Gradient-Based Explanations
di: Bordt, Sebastian, et al.
Pubblicazione: (2022)

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
di: Cho, Seonglae, et al.
Pubblicazione: (2025)

Beyond Kemeny Medians: Consensus Ranking Distributions Definition, Properties and Statistical Learning
di: Clémençon, Stephan, et al.
Pubblicazione: (2026)

Active Bipartite Ranking with Smooth Posterior Distributions
di: Cheshire, James, et al.
Pubblicazione: (2026)

Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
di: Eyring, Luca, et al.
Pubblicazione: (2025)

Opening the Black-Box: A Systematic Review on Explainable AI in Remote Sensing
di: Höhl, Adrian, et al.
Pubblicazione: (2024)

Discovering Chunks in Neural Embeddings for Interpretability
di: Wu, Shuchen, et al.
Pubblicazione: (2025)

Right on Time: Revising Time Series Models by Constraining their Explanations
di: Kraus, Maurice, et al.
Pubblicazione: (2024)

PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
di: Koromilas, Panagiotis, et al.
Pubblicazione: (2026)

Rethinking Concept Bottleneck Models: From Pitfalls to Solutions
di: Tapli, Merve, et al.
Pubblicazione: (2026)

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

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

On Ranking-based Tests of Independence
di: Limnios, Myrto, et al.
Pubblicazione: (2024)

A Systematic Study of In-the-Wild Model Merging for Large Language Models
di: Hitit, Oğuz Kağan, et al.
Pubblicazione: (2025)

Black-Box Time-Series Domain Adaptation via Cross-Prompt Foundation Models
di: Furqon, M. T., et al.
Pubblicazione: (2025)

Doing well with less! On Sampling Techniques for Empirical Pairwise Loss Estimation/Minimization
di: Davy, Louise, et al.
Pubblicazione: (2026)

A Statistical Learning View of Simple Kriging
di: Siviero, Emilia, et al.
Pubblicazione: (2022)

SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions
di: Bader, Jessica, et al.
Pubblicazione: (2025)

Tailoring Mixup to Data for Calibration
di: Bouniot, Quentin, et al.
Pubblicazione: (2023)

Motif-guided Time Series Counterfactual Explanations
di: Li, Peiyu, et al.
Pubblicazione: (2022)

Accelerating Time Series Foundation Models with Speculative Decoding
di: Subbaraman, Pranav, et al.
Pubblicazione: (2025)

How to Merge Your Multimodal Models Over Time?
di: Dziadzio, Sebastian, et al.
Pubblicazione: (2024)

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

Asynchronous Gossip Algorithms for Rank-Based Statistical Methods
di: Van Elst, Anna, et al.
Pubblicazione: (2025)

TimeX++: Learning Time-Series Explanations with Information Bottleneck
di: Liu, Zichuan, et al.
Pubblicazione: (2024)

Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
di: Girrbach, Leander, et al.
Pubblicazione: (2025)

ImputeGAP: A Comprehensive Library for Time Series Imputation
di: Nater, Quentin, et al.
Pubblicazione: (2025)

LightSAE: Parameter-Efficient and Heterogeneity-Aware Embedding for IoT Multivariate Time Series Forecasting
di: Ren, Yi, et al.
Pubblicazione: (2025)

Feature Impact Analysis on Top Long-Jump Performances with Quantile Random Forest and Explainable AI Techniques
di: Gan, Qi, et al.
Pubblicazione: (2025)

Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means
di: Van Elst, Anna, et al.
Pubblicazione: (2025)