AI Paper Atlas

Research map / Time series / Long-term forecasting

Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting

Yuxuan Shu, Vasileios Lampos

AAAI 2026 · Time series › Long-term forecasting · approach: Graph-based multivariate forecasting · 3 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
replace naive attention with MVCA (ablation)PatchTST, Samformer, iTransformer · ILI tasksMAE: -10.7% MAE on averageImproved
replace naive attention with MVCA (ablation)PatchTST · ILI-US2 H=28MAE: 1.1525 -> 0.8765Improved
remove attention module from base models (ablation)iTransformer/Samformer/PatchTST · ILI tasksMAENo clear effect
replace naive attention with FEDformer FED attention (ablation)base models · ILI tasksMAE: e.g. PatchTST 1.1525 -> 1.4953 (ILI-US2 H=28)Hurt
replace naive attention with FNet attention (ablation)base models · ILI tasksMAEHurt
use MVCA instead of VDAB attention (ablation)base models · ILI tasksMAE: -3.5% MAEImproved
use MVCA instead of VDAB inside Sonnet (ablation)Sonnet · ILI and WEA (32 tasks)MAE: -3.6% MAE on averageImproved
use MVCA instead of naive attention inside Sonnet (ablation)Sonnet · ILI and WEA (32 tasks)MAE: -7% MAE on averageImproved
use MVCA instead of FED attention inside Sonnet (ablation)Sonnet · ILI and WEA (32 tasks)MAE: -51.5% MAEImproved
use Sonnet instead of DeformTimeSonnet · 47 tasks overallMAE: -2.2% MAE on average (best on 34 of 47)Improved
use Sonnet instead of baselines on ETTSonnet · ETTh1/ETTh2MAE: ETTh2 H=720: 0.3640 -> 0.4335Hurt
use Sonnet on tasks other than ETTSonnet · non-ETT tasksMAE: -3.3% MAE on averageImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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