AI Paper Atlas

Research map / Time series / Long-term forecasting

Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks

Yijing Liu, Qinxian Liu, Jian-Wei Zhang, Haozhe Feng, Zhongwei Wang, Zihan Zhou, Wei Chen

NeurIPS 2022 · 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 TPG-built graph with the dataset prior structure (ablation)TPGNN · PEMS-D7 horizon 12MAE: 3.701 -> 3.215Improved
replace TPG graph with prior structure (ablation)TPGNN · PEMS-D7 horizon 12RMSE: 7.473 -> 6.559Improved
add time-varying coefficients instead of static learnable ones (ablation)TPGNN · PEMS-D7 horizon 12MAE: 3.480 -> 3.215Improved
add average coefficients (overview, Eq. 6) (ablation)TPGNN · PEMS-D7 horizon 12MAE: 3.330 -> 3.215Improved
add normalization factor (Eq. 7) (ablation)TPGNN · PEMS-D7 horizon 12MAE: 3.261±0.035 -> 3.215±0.014No clear effect
add multiple parameter matrices (K-matrices) (ablation)TPGNN · PEMS-D7 horizon 12MAPE(%): 8.406±0.245 -> 8.221±0.035Improved
use TPGNN instead of static/attention graph baselinesTPGNN vs baselines · Synthetic next-stepMFE: 0.1653 -> 0.1266Improved
use TPGNN instead of Graph WavenetTPGNN · Synthetic next-stepMAE: 0.01049 -> 0.01015Improved
increase polynomial order K from 1 to 4 (ablation)TPGNN · Synthetic MFEMFEHurt
use TPGNN instead of MTGNN on Solar-EnergyTPGNN · Solar-Energy horizon 24RSE: 0.4270 -> 0.3498Improved
use TPGNN instead of MTGNN on ElectricityTPGNN · Electricity horizon 3RSE: 0.0745 -> 0.0627Improved
use TPGNN instead of TPA-LSTM on Exchange-RateTPGNN · Exchange-Rate horizon 12RSE: 0.0341 -> 0.0350No clear effect

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