FL-trafficNet: a hybrid federated transformer-GNN framework with dual attention for smart routing in IoV and VANET environments
Pallati Narsimhulu, Rashmi Sahay · 2026
Read FL-trafficNet: a hybrid federated transformer-GNN framework with dual attention for smart routing in IoV and VANET environments by Pallati Narsimhulu, Rashmi Sahay (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13429630.txt.
Description
Pallati Narsimhulu and Rashmi Sahay propose FL-trafficNet, a routing system for connected vehicles and roadside sensors in smart cities. Huge live data streams now choke central servers, causing delays and wasteful routing for cars that talk to each other and to the road.
The framework joins transformer models, which track change over time, with graph networks, which read road layout, plus dual attention to pick the features that matter in space and time. Federated learning lets vehicles and roadside units train locally instead of shipping raw data to the cloud. Cities get faster, private routing that learns where traffic actually flows.
Catalog record
| CREATOR | Pallati Narsimhulu, Rashmi Sahay |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 61 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |