arXiv Machine Learning October 5, 2026 By Zeyu Shi, Yanhui Luo, Ziming Hong, Chongyang Gao, Kezhen Chen, Shanshan Ye, Lixu Wang

On Unlearning for Time-series Forecasting

Read the original on arXiv Machine Learning →

The paper introduces RDTU, a Residual Diffusion framework designed to enable efficient unlearning in time‑series forecasting models. RDTU first generates a deletion‑compatible base forecast using a retained‑set neural tangent kernel predictor, then assesses the structural support of affected windows via volume contribution metrics, and finally applies a diffusion model to produce residual corrections that approximate counterfactual forecasts. These pseudo‑labels guide a lightweight update, resulting in models that closely match those obtained by exact retraining after data deletion.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

1d ago

Retrieval Is Not Enough: Refreshing Memory for Frozen Time-Series Forecasters

arXiv:2610.07834v1 Announce Type: new Abstract: Retrieval-augmented time-series forecasting uses the continuations of historical segments similar to the current context as references for a forecaster...

By Chao He, Jianyu Xu, Xinyi Guo, Ruiqi Liu, Haobin Ding, Ruiqi He, Dongqing Song

rag benchmarks safety

arXiv AI

Aug 7

Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy Denoising

arXiv:2510. 05589v3 Announce Type: replace-cross Abstract: Effective time series forecasting enables various real-world applications, benefiting from the proliferation of mobile devices.

By Kangjia Yan, Chenxi Liu, Hao Miao, Xinle Wu, Yan Zhao, Chenjuan Guo, Bin Yang

llms efficiency benchmarks

arXiv AI

Sep 4

RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series Forecasting

RATL is a plug‑in method for multivariate time‑series forecasting that uses a frozen base forecaster to build a memory of its historical forecast residuals. During inference, RATL retrieves residual trajectories from similar past contexts and employs a set‑aware router to combine them, providing learned feedback correction. Experiments demonstrate that this residual‑retrieval approach improves the performance of the base forecaster across various benchmarks and backbones.

By Yuchen He, Yueyang Cang, Zhiyuan Ning, Ningyu Wang, Li Shi

rag benchmarks

arXiv Machine Learning

Jun 2

Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification

arXiv:2602. 16224v2 Announce Type: replace Abstract: Time series data are prone to noise in various domains, and training samples may contain low-predictability patterns that deviate from the normal data distribution, leading to training instability or convergence to poor local minima.

By Xu Zhang, Peng Wang, Yichen Li, Wei Wang

safety

arXiv AI

Jun 18

Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs

arXiv:2507. 04219v5 Announce Type: replace-cross Abstract: Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data.

By Yan Scholten, Sophie Xhonneux, Leo Schwinn, Stephan G\"unnemann

llms fine-tuning safety

arXiv AI

Oct 1

Pseudo-Label-Triggered Retraining from Forecast Errors for Online Time Series Forecasting

arXiv:2609.39789v1 Announce Type: cross Abstract: Real-world time series forecasting systems operate under non-stationary data streams, where forecasting performance may degrade over time. Although r...

By Yeryeong Kwak, Yoo-Min Jung, Jonghun Park

benchmarks

One email a morning, machine-written

Related stories

Retrieval Is Not Enough: Refreshing Memory for Frozen Time-Series Forecasters

Invariant Representation Learning for Source-Free Time Series Forecasting with LLM-Centric Proxy Denoising

RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series Forecasting

Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification

Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs

Pseudo-Label-Triggered Retraining from Forecast Errors for Online Time Series Forecasting