AI Paper Atlas

Research map / Time series / Causal and generative time series

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

Zichuan Liu, Tianchun Wang, Jimeng Shi, Xu Zheng, Zhuomin Chen, Lei Song, Wenqian Dong, Jayantha Obeysekera, Farhad Shirani, Dongsheng Luo

ICML 2024 · Time series › Causal and generative time series · approach: State-space and latent dynamics forecasting · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes TimeX++, an information-bottleneck-based framework for learning faithful, in-distribution explanations of deep time-series models, addressing trivial solutions and distributional shift in existing explainability measures.

Problem

Explaining deep learning models on time series is important, but existing explainability objectives may yield trivial solutions and suffer from distributional shift issues.

Approach

Frames time-series explanation as an information bottleneck problem, learning a generative explainer that selects salient time-series segments while avoiding trivial solutions and out-of-distribution artifacts.

Limitations

Experimental setup

Builds on: TimeX

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy