AI Paper Atlas

Research map / Time series / Long-term forecasting

What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies

Fan Zhang, Shiming Fan, Hua Wang

ICML 2026 · Time series › Long-term forecasting · approach: Graph-based multivariate forecasting · 0 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 the sparse dependency bottleneck (Top-K cross-variable routing) (ablation)MS-FLOW · Solar-EnergyMSE: 0.210 -> 0.173Improved
add patch-wise temporal interaction (ablation)MS-FLOW · ElectricityMSE: 0.135 -> 0.132Improved
add the feed-forward network after dependency injection (ablation)MS-FLOW · ElectricityMSE: 0.146 -> 0.132Improved
use Top-K sparse routing instead of dense (K=C) interaction (ablation)MS-FLOW · ElectricityMSE: 0.139 -> 0.132Improved
use Top-K instead of dense interaction (ablation)MS-FLOW · ETTm2MSE: 0.166 -> 0.166No clear effect
select neighbors by Top-K similarity instead of random-K (ablation)MS-FLOW · Solar-EnergyMSE: 0.179 -> 0.173Improved
use sample-adaptive graph instead of static graph (ablation)MS-FLOW · Solar-EnergyMSE: 0.196 -> 0.173Improved
use average pooling instead of max pooling for variable states (ablation)MS-FLOW · WeatherMSE: 0.172 -> 0.150Improved
use shared window-level graph instead of per-patch graphs (ablation)MS-FLOW · WeatherMSE: 0.155 -> 0.150Improved
Top-K sparse routing reduces edges touching noisy channels (ablation)MS-FLOW · Electricity with 25 noisy channelspollution hit rate (%): 7.79% -> 3.80%Improved
use MS-FLOW instead of TimeFilter on TrafficMS-FLOW · Traffic (L=96)MSE: 0.407 -> 0.440Hurt
increase encoder depth (layers) (ablation)MS-FLOW · ETTh1, Electricity, TrafficMSENo clear effect

Earlier methods this paper compares with

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