Dual-adaptive imputation graph neural network for knowledge-aware recommendation
Zhenge Huo, Huanhuan Liu, Xinglong Wu, Chenxing Xia, Bin Ge, Yu Zhang · 2026
Read Dual-adaptive imputation graph neural network for knowledge-aware recommendation by Zhenge Huo, Huanhuan Liu, Xinglong Wu, Chenxing Xia, Bin Ge, Yu Zhang (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/PMC13518815.txt.
Description
Zhenge Huo and five colleagues introduce DAIGNN in 2026, a recommendation system that borrows facts from a knowledge graph to suggest items. Such systems ease sparse data and cold starts for new users, though many underuse the user-item interaction record and blend side information poorly.
DAIGNN first fills gaps by building an imputation graph from guessed ratings based on similarity, which thickens the sparse interaction network. Extra information about users and items then enriches the graph. A dual-adaptive fusion step learns how much weight each source deserves. Tests on four real datasets beat leading rivals, averaging 3.1 percent higher AUC and 2.0 percent higher F1 score.
Catalog record
| CREATOR | Zhenge Huo, Huanhuan Liu, Xinglong Wu, Chenxing Xia, Bin Ge, Yu Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 79813 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |