Identifying hot-spot pathways in fishery science and technology innovation through temporal heterogeneous graph neural networks
Fengwei Zhang, Xiaolin Wang, Jing Hu · 2026
Read Identifying hot-spot pathways in fishery science and technology innovation through temporal heterogeneous graph neural networks by Fengwei Zhang, Xiaolin Wang, Jing Hu (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/PMC13562653.txt.
Description
Fengwei Zhang and two colleagues teach a neural network to spot where fishery research and technology are heading next. Funding bodies must bet on promising lines early, and older foresight methods miss how research networks shift over time. Their 2026 model, DTH-GNN, builds a changing knowledge graph from 2010 to 2024 sources: 32,847 publications, 8,956 patents, and 1,856 projects. A graph encoder reads the mixed node types, while a memory module follows how links evolve year by year.
The system predicted future links with a score of 0.934, clearly beating three rival graph methods after leakage checks. Timing information carried about as much predictive weight as network structure, at 31.8 against 29.1 percent of the shared information. Three rising pathways passed expert review with strong agreement: smart aquaculture, a green seed industry, and ecological fisheries. The authors offer the rankings as evidence for where fishery investment may pay off.
Catalog record
| CREATOR | Fengwei Zhang, Xiaolin Wang, Jing Hu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 211963 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |