GraphSparseNet: a Novel Method for Large Scale Traffic Flow Prediction
Summary: GraphSparseNet (GSNet): GNN forecasting using a Feature Extractor and Relational Compressor to reduce graph complexity to linear time/space. 3.51× training speedup vs. SOTA linear baselines on real traffic data while preserving accuracy, offering a scalable alternative to sparsification/decomposition/kernel fixes. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Weiyang Kong
- 2. Kaiqi Wu
- 3. Sen Zhang
- 4. Yubao Liu
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 1 of 1 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 3,234 | BigST: Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks | 2024 | VLDB | 7.3355287e-05 |
Previous
Page 1 / 1
Next