Pith. sign in

REVIEW 3 cited by

TimeX++: Learning Time-Series Explanations with Information Bottleneck

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.09308 v1 pith:AL2AI5FM submitted 2024-05-15 cs.LG cs.AI

classification cs.LGcs.AI
keywords seriestimetimexfunctioninformationissueslearningobjective
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Explaining deep learning models operating on time series data is crucial in various applications of interest which require interpretable and transparent insights from time series signals. In this work, we investigate this problem from an information theoretic perspective and show that most existing measures of explainability may suffer from trivial solutions and distributional shift issues. To address these issues, we introduce a simple yet practical objective function for time series explainable learning. The design of the objective function builds upon the principle of information bottleneck (IB), and modifies the IB objective function to avoid trivial solutions and distributional shift issues. We further present TimeX++, a novel explanation framework that leverages a parametric network to produce explanation-embedded instances that are both in-distributed and label-preserving. We evaluate TimeX++ on both synthetic and real-world datasets comparing its performance against leading baselines, and validate its practical efficacy through case studies in a real-world environmental application. Quantitative and qualitative evaluations show that TimeX++ outperforms baselines across all datasets, demonstrating a substantial improvement in explanation quality for time series data. The source code is available at \url{https://github.com/zichuan-liu/TimeXplusplus}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregate

    cs.LG 2025-12 conditional novelty 7.0 of 10

    MAGNETS learns unsupervised, mask-based concepts to make time-series regression predictions additively interpretable, recovering ground-truth temporal rules on synthetic tasks and beating interpretable baselines on mo...

  2. Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A budgeted information-bottleneck forecaster matches black-box multivariate accuracy while using only 14–20% of history tokens as architecturally faithful explanations.

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

    cs.LG 2026-01 conditional novelty 6.0 of 10

    TimeSAE trains a sparse autoencoder with counterfactual and consistency losses to explain black-box time series predictions, claiming better faithfulness and out-of-distribution robustness than eight baselines.

Pith tools