HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Traffic Prediction On Pems08

평가 지표

MAE@1h

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	MAE@1h	Paper Title	Repository
PDFormer	13.58	PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction
FasterSTS	13.60	FasterSTS: A Faster Spatio-Temporal Synchronous Graph Convolutional Networks for Traffic flow Forecasting	-
STAEformer	13.46	STAEformer: Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting
DTRformer	13.17	Dynamic Trend Fusion Module for Traffic Flow Prediction
CorrSTN	14.27	A Correlation Information-based Spatiotemporal Network for Traffic Flow Forecasting
DDGCRN	14.40	A Decomposition Dynamic graph convolutional recurrent network for traffic forecasting
Cy2Mixer	13.53	Enhancing Topological Dependencies in Spatio-Temporal Graphs with Cycle Message Passing Blocks
LightCTS	-	LightCTS: A Lightweight Framework for Correlated Time Series Forecasting
HTVGNN	13.24	A novel hybrid time-varying graph neural network for traffic flow forecasting	-
PDG2Seq	13.60	PDG2Seq: Periodic Dynamic Graph to Sequence Model for Traffic Flow Prediction
PM-DMNet(P)	13.55	Pattern-Matching Dynamic Memory Network for Dual-Mode Traffic Prediction
PM-DMNet(R)	13.40	Pattern-Matching Dynamic Memory Network for Dual-Mode Traffic Prediction
STWave	13.42	When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks

0 of 13 row(s) selected.