Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385270240> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4385270240 abstract "Traffic forecasting is crucial for public safety and resource optimization, yet is very challenging due to the temporal changes and the dynamic spatial correlations of the traffic data. To capture these intricate dependencies, spatio-temporal networks, such as recurrent neural networks with graph convolution networks, graph convolution networks with temporal convolution networks, and temporal attention networks with full graph attention networks, are applied. However, previous spatio-temporal networks are based on end-to-end training and thus fail to handle the distribution shift in the non-stationary traffic time series. On the other hand, the efficient and effective algorithm for modeling spatial correlations is still lacking in prior networks.In this paper, rather than proposing yet another end-to-end model, we aim to provide a novel disentangle-fusion framework STWave to mitigate the distribution shift issue. The framework first decouples the complex traffic data into stable trends and fluctuating events, followed by a dual-channel spatio-temporal network to model trends and events, respectively. Finally, reasonable future traffic can be predicted through the fusion of trends and events. Besides, we incorporate a novel query sampling strategy and graph wavelet-based graph positional encoding into the full graph attention network to efficiently and effectively model dynamic spatial correlations. Extensive experiments on six traffic datasets show the superiority of our approach, i.e., the higher forecasting accuracy with lower computational cost." @default.
- W4385270240 created "2023-07-27" @default.
- W4385270240 creator A5008135430 @default.
- W4385270240 creator A5019091721 @default.
- W4385270240 creator A5022580520 @default.
- W4385270240 creator A5031468255 @default.
- W4385270240 creator A5034407627 @default.
- W4385270240 creator A5052635380 @default.
- W4385270240 creator A5064637838 @default.
- W4385270240 date "2023-04-01" @default.
- W4385270240 modified "2023-10-12" @default.
- W4385270240 title "When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks" @default.
- W4385270240 cites W1973943669 @default.
- W4385270240 cites W2069929199 @default.
- W4385270240 cites W2158787690 @default.
- W4385270240 cites W2163922914 @default.
- W4385270240 cites W2794284562 @default.
- W4385270240 cites W2795273206 @default.
- W4385270240 cites W2903871660 @default.
- W4385270240 cites W2919115771 @default.
- W4385270240 cites W2962756421 @default.
- W4385270240 cites W2965341826 @default.
- W4385270240 cites W2996847713 @default.
- W4385270240 cites W2997848713 @default.
- W4385270240 cites W2998559444 @default.
- W4385270240 cites W3019166713 @default.
- W4385270240 cites W3035580605 @default.
- W4385270240 cites W3093761440 @default.
- W4385270240 cites W3094009742 @default.
- W4385270240 cites W3097237405 @default.
- W4385270240 cites W3103720336 @default.
- W4385270240 cites W3105705953 @default.
- W4385270240 cites W3139491754 @default.
- W4385270240 cites W3170140111 @default.
- W4385270240 cites W3174022889 @default.
- W4385270240 cites W3175016653 @default.
- W4385270240 cites W3175924508 @default.
- W4385270240 cites W3177318507 @default.
- W4385270240 cites W3195970356 @default.
- W4385270240 cites W4249224151 @default.
- W4385270240 cites W4255272544 @default.
- W4385270240 cites W4291910369 @default.
- W4385270240 cites W4306316920 @default.
- W4385270240 doi "https://doi.org/10.1109/icde55515.2023.00046" @default.
- W4385270240 hasPublicationYear "2023" @default.
- W4385270240 type Work @default.
- W4385270240 citedByCount "1" @default.
- W4385270240 countsByYear W43852702402022 @default.
- W4385270240 crossrefType "proceedings-article" @default.
- W4385270240 hasAuthorship W4385270240A5008135430 @default.
- W4385270240 hasAuthorship W4385270240A5019091721 @default.
- W4385270240 hasAuthorship W4385270240A5022580520 @default.
- W4385270240 hasAuthorship W4385270240A5031468255 @default.
- W4385270240 hasAuthorship W4385270240A5034407627 @default.
- W4385270240 hasAuthorship W4385270240A5052635380 @default.
- W4385270240 hasAuthorship W4385270240A5064637838 @default.
- W4385270240 hasConcept C124101348 @default.
- W4385270240 hasConcept C132525143 @default.
- W4385270240 hasConcept C154945302 @default.
- W4385270240 hasConcept C41008148 @default.
- W4385270240 hasConcept C45347329 @default.
- W4385270240 hasConcept C47432892 @default.
- W4385270240 hasConcept C50644808 @default.
- W4385270240 hasConcept C80444323 @default.
- W4385270240 hasConceptScore W4385270240C124101348 @default.
- W4385270240 hasConceptScore W4385270240C132525143 @default.
- W4385270240 hasConceptScore W4385270240C154945302 @default.
- W4385270240 hasConceptScore W4385270240C41008148 @default.
- W4385270240 hasConceptScore W4385270240C45347329 @default.
- W4385270240 hasConceptScore W4385270240C47432892 @default.
- W4385270240 hasConceptScore W4385270240C50644808 @default.
- W4385270240 hasConceptScore W4385270240C80444323 @default.
- W4385270240 hasFunder F4320321001 @default.
- W4385270240 hasFunder F4320321133 @default.
- W4385270240 hasLocation W43852702401 @default.
- W4385270240 hasOpenAccess W4385270240 @default.
- W4385270240 hasPrimaryLocation W43852702401 @default.
- W4385270240 hasRelatedWork W1982584880 @default.
- W4385270240 hasRelatedWork W2068395868 @default.
- W4385270240 hasRelatedWork W2320412164 @default.
- W4385270240 hasRelatedWork W2347219288 @default.
- W4385270240 hasRelatedWork W2355873293 @default.
- W4385270240 hasRelatedWork W2461636238 @default.
- W4385270240 hasRelatedWork W2541950815 @default.
- W4385270240 hasRelatedWork W3045843715 @default.
- W4385270240 hasRelatedWork W4226487993 @default.
- W4385270240 hasRelatedWork W4291617047 @default.
- W4385270240 isParatext "false" @default.
- W4385270240 isRetracted "false" @default.
- W4385270240 workType "article" @default.