Leveraging similarity and community-based features for link prediction in temporal social networks using attention-enabled LSTM
Rohit Ahuja, Simranjit Kaur, Harish Kumar Shakya, Shashank Sheshar Singh · 2025
Read Leveraging similarity and community-based features for link prediction in temporal social networks using attention-enabled LSTM by Rohit Ahuja, Simranjit Kaur, Harish Kumar Shakya, Shashank Sheshar Singh (2025) 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-12753736.txt.
Description
Rohit Ahuja and co-authors predict which links will form next in a changing social network. Their 2025 paper notes that most predictors read a single snapshot, while real networks shift over time. Group structure helps too, since most new ties form inside communities.
Their framework, SimCom-AN-LSTM, feeds sequences of snapshots to a memory network. It mixes closeness scores between users with community features. An attention step gives extra weight to the features that pay off most. The model learns how ties form over time at local and whole-network scale. In tests it beat leading single methods. The authors aim it at friend suggestion and network analysis for platforms that change daily.
Catalog record
| CREATOR | Rohit Ahuja, Simranjit Kaur, Harish Kumar Shakya, Shashank Sheshar Singh |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 78 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |