AI Paper Atlas

Research map / Time series / Long-term forecasting

BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis

Zelin Ni, Hang Yu, Shizhan Liu, Jianguo Li, Weiyao Lin

NeurIPS 2023 · Time series › Long-term forecasting · approach: Attention for time series 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
replace learnable basis with fixed sine/cosine basis (ablation)BasisFormer · ElectricityMSE (avg): +9.3%Hurt
replace learnable basis with random sine/cosine basis (ablation)BasisFormer · ElectricityMSE (avg): +9.1%Hurt
replace learnable basis with covariate embedding (ablation)BasisFormer · ElectricityMSE (avg): +5.3%Hurt
add InfoNCE loss to basis module (ablation)BasisFormer · ElectricityMSE (avg): 0.204 -> -5.2%Improved
add smoothness loss to basis module (ablation)BasisFormer · ElectricityMSE (avg): 0.204 -> -2.0%Improved
use both InfoNCE and smoothness losses (ablation)BasisFormer · ElectricityMSE (avg): 0.204 -> -7.2%Improved
increase Coef heads from 4 to 16 (ablation)BasisFormer · ElectricityMSE (avg): 0.201 -> 0.189Improved
increase Coef heads from 16 to 32 (ablation)BasisFormer · ElectricityMSE (avg): 0.189 -> 0.199Hurt
vary number of bases N from 1 to 10 (ablation)BasisFormer · ElectricityMSE (avg): 0.196 -> 0.187Improved
increase number of bases N from 10 to 20 (ablation)BasisFormer · ElectricityMSE (avg): 0.187 -> 0.190No clear effect
add self-supervised coef module supervision to FEDformer covariatesFEDformer · ElectricityMSE (avg): 0.214 -> 0.204Improved
add self-supervised coef module supervision to Autoformer covariatesAutoformer · ElectricityMSE (avg): 0.227 -> 0.214Improved

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