AI Paper Atlas

Research map / Time series / Long-term forecasting

Predicting the Future by Retrieving the Past

Dazhao Du, Tao Han, Song Guo

AAAI 2026 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add PFRP global retrievalSparseTSF · TrafficMSE: 0.2404 -> 0.1919Improved
add PFRP global retrievalSparseTSF · ElectricityMSE: 0.4968 -> 0.3561Improved
add PFRP global retrievalDLinear · WeatherMSE: 0.7250 -> 0.6751Improved
add PFRP global retrievalSparseTSF, DLinear, PatchTST, TimesNet · ETT datasetsMSE: average gains 3.4%, 3.1%, 1.6%, 2.2% on ETTh1/h2/m1/m2Improved
add confidence gate (ablation)PFRP · ElectricityMSE: 0.3960 -> 0.3561Improved
add output gate (ablation)PFRP · ElectricityMSE: 0.5140 -> 0.3561Improved
add local prediction model to global-only PFRP (ablation)PFRP · TrafficMSE: 0.1686 -> 0.1919Hurt
add local prediction model to global-only PFRP (ablation)PFRP · ElectricityMSE: 0.3952 -> 0.3561Improved
use feature cosine similarity instead of DTW retrieval (ablation)PFRP · ElectricityMSE: 0.3659 -> 0.3561Improved
train encoder with predictive contrastive learning instead of standard contrastive learning (ablation)PFRP · ElectricityMSE: 0.3833 -> 0.3561Improved
swap MLP encoder for PatchTST or TimesNet (ablation)PFRP · Traffic/ElectricityMSE: Traffic TimesNet 0.1754 vs MLP 0.1919; Electricity PatchTST 0.3492Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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