Skip to content
Open access

DeCyReM: De-Cycled Residual Memory with Utility-Gated Retrieval for Traffic Flow Forecasting

Sep 2026 · Mathematics · Vol 14, pp. 3207 · 0 citations

TL;DR

DeCyReM converts reusable historical error experience into selective forecast corrections, providing an error-centric approach to forecasting abrupt and irregular traffic states.

Abstract

Accurate traffic-flow forecasting remains challenged by abrupt and irregular states even after dominant periodic patterns are captured. Existing predictors model the resulting difficult errors implicitly through their parameters and cannot explicitly reuse specific historical errors at inference. We find that multi-horizon base-prediction errors recur conditionally across similar de-cycled node-local states. Based on this observation, we propose De-Cycled Residual Memory with Utility-Gated Retrieval (DeCyReM). It constructs queries from de-cycled residuals, spatial context, and temporal information, retrieves historical base errors from a node-local difficult-and-diverse memory, and uses a utility gate to control their contribution as forecast corrections. Across PeMS03, PeMS04, PeMS07, and PeMS08, DeCyReM records the numerically lowest reported value in seven of the twelve dataset–metric combinations and ranks within the top three in eleven. Ablation and mechanism analyses show that retrieval improves error alignment and mainly benefits difficult samples; similarity alone cannot determine correction utility, whereas gate values track helpful retrievals. Case and robustness analyses further characterize successful correction, safe attenuation, and mismatch-induced failure, identifying reliable key–value correspondence as essential. Overall, DeCyReM converts reusable historical error experience into selective forecast corrections, providing an error-centric approach to forecasting abrupt and irregular traffic states.

Read PDF

Similar papers

Open access Sep 2026

MURECAST: Memory-Based Utility-Aligned Residual Evidence with Calibrated Activation for Selective Correction of Traffic-Flow Forecasts

This work proposes Memory-Based Utility-Aligned Residual Evidence with Calibrated Activation for Selective Correction of Traffic-Flow Forecasts (MURECAST), which treats historical residuals as candidate interventions and ranks first in dataset–metric comparisons.

Xue-Ting Jin, Jin-Feng Xu, Qian-Xin Xie et al. · 0 citations
#machine learning Preprint Oct 2026

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

Retrieval-augmented time-series forecasting uses the continuations of historical segments similar to the current context as references for a forecaster. Most existing methods build the retrieval memory once from the training segment, leaving observations revealed after deployment unavailable as references, and generall...

Chao-Zhong He, Jian-Yu Xu, Xin-Yi Guo et al. · 0 citations
#artificial intelligence Preprint Sep 2026

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

Overall, RATL shifts the retrieved object from historical target values to base-model-specific historical forecast errors, providing a plug-in, residual-memory-based paradigm for learned feedback correction in continuous-output forecasting.

Yu-Chen He, Yueyang Cang, Zhi-Yuan Ning et al. · 1 citation · ⚡1
Preprint Aug 2026

RiskTraf: Risk-Extrapolated Residual Learning for Multi-Variate Traffic Flow Prediction

PEMSB-3V, a public benchmark suite that preserves raw flow, speed, and occupancy measurements from PeMS detectors for flow prediction, and RiskTraf, a model-agnostic risk-extrapolated residual plug-in that consistently improves diverse forecasting backbones and outperforms debiasing and distribution-shift adaptation me...

Guangyu Wang, Zhida Liu · 0 citations
#machine learning Preprint Oct 2026

GRAM: Correcting Frozen Time-Series Foundation Models via Graph-Retrieved Amplitude Memory

Time-series foundation models (TSFMs) enable zero-shot forecasting through large-scale cross-domain pretraining, while retrieval augmentation further improves their performance by leveraging historical information. However, existing methods typically correct TSFM forecasts using the ground-truth futures of similar hist...

Xiao-Yun Yu, Xiangfei Qiu, Yong-Gui Huang et al. · 0 citations
#artificial intelligence Preprint Oct 2026

SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting

This work proposes SEER (Self-Evolving Event Reasoning and Retrieval), a closed-loop framework that dynamically optimizes event conditioning for time series forecasting and consistently outperforms state-of-the-art time series foundation models and language model baselines.

Ming-Tian Tan, Palash Goyal, Mihir Parmar et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.