Haixin Wang, Qianru Zhang, Hongzhi Yin, Siu-Ming Yiu, Xinyi Gao
We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| lizzyhku/TP | — | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| Teacher | Not yet run | lizzyhku/TP/model/Teacher.py pointer only (licence: NONE) · get_code("9df45c1073f037a9") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Graph neural networks (GNNs) have gained considerable attention in recent years for traffic flow prediction due to their ability to learn spatio-temporal pattern representations through a graph-based message-passing framework. Although GNNs have shown great promise in handling traffic datasets, their deployment in real-life applications has been hindered by scalability constraints arising from high-order message passing. Additionally, the over-smoothing problem of GNNs may lead to indistinguishable region representations as the number of layers increases, resulting in performance degradation. To address these challenges, we propose a new knowledge distillation paradigm termed LightST that transfers spatial and temporal knowledge from a highcapacity teacher to a lightweight student. Specifically, we introduce a spatio-temporal knowledge distillation framework that helps student MLPs capture graph-structured global spatio-temporal patterns while alleviating the over-smoothing effect with adaptive knowledge distillation. Extensive experiments verify that LightST significantly speeds up traffic flow predictions by 5X to 40X compared to state-of-the-art spatiotemporal GNNs, all while maintaining superior accuracy.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2501.10459")
get_code_for_paper("2501.10459")
have("2501.10459")
Connect an agent — have() is free.