Summary of Temporal Link Prediction Using Graph Embedding Dynamics, by Sanaz Hasanzadeh Fard et al.
Temporal Link Prediction Using Graph Embedding Dynamics
by Sanaz Hasanzadeh Fard, Mohammad Ghassemi
First submitted to arxiv on: 15 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Social and Information Networks (cs.SI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel perspective on temporal link prediction in dynamic networks by treating nodes as Newtonian objects and incorporating velocity to predict network dynamics. The approach improves accuracy and explainability by computing specific node dynamics rather than overall dynamics. Experimental results show an improvement of 17.34% (AUROC) in predicting future collaboration efficacy in co-authorship networks using two datasets, including PubMed’s 17 years of co-authorship data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding connections between things that change over time. It’s like trying to predict who will work together on a project based on past projects. The usual way to do this is by looking at the whole network and saying “this is what’s happening overall”. But this new approach looks at each person (or thing) separately, seeing how they’re moving and changing over time. This makes it better at predicting future connections and also helps us understand why it made those predictions. It works really well on a big dataset of scientists who worked together on papers. |
