AI Paper Atlas

Research map / Time series / Long-term forecasting

CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement

Qihe Huang, Lei Shen, Ruixin Zhang, Shouhong Ding, Binwu Wang, Zhengyang Zhou, Yang Wang

NeurIPS 2023 · Time series › Long-term forecasting · approach: Graph-based multivariate forecasting

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 Cross-Scale GNN (ablation)CrossGNN · Weather T=96MSE: 0.175 -> 0.159Improved
add Cross-Scale GNN (ablation)CrossGNN · ETTm2 T=96MSE: 0.200 -> 0.176Improved
add adaptive multi-scale identifier (vs fixed pooling lengths) (ablation)CrossGNN · Weather T=96MSE: 0.167 -> 0.159Improved
add adaptive multi-scale identifier (ablation)CrossGNN · Traffic T=96MSE: 0.585 -> 0.570Improved
add heterogeneous connections (ablation)CrossGNN · ETTm2 T=96MSE: 0.190 -> 0.176Improved
add Cross-Variable GNN (homogeneous and heterogeneous) (ablation)CrossGNN · Weather T=96MSE: 0.174 -> 0.159Improved
add Cross-Variable GNN (ablation)CrossGNN · Traffic T=96MSE: 0.588 -> 0.570Improved
use CrossGNN instead of best Transformer-based methodCrossGNN · 8 MTS datasetsMSE: 10.43% reductionImproved
use CrossGNN instead of MTGNNCrossGNN · 8 MTS datasetsMSE: 22.57% reductionImproved
use CrossGNN instead of PatchTSTCrossGNN · Electricity T=96MSE: 0.159 -> 0.173Hurt
lower SNR from 100db to 0dbCrossGNN vs ETSformer, MTGNN · ETTm2MSE: 0.177 vs 0.191 and 0.205Improved
increase number of scales from 4 to 8CrossGNN · Weather and TrafficMSE and MAENo clear effect

Later papers that compared with this method

2 later accepted papers report CrossGNN as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

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