An LLM-guided framework for link prediction in homogeneous graphs
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract As social networks grow, link prediction has become vital in network analysis, estimating the likelihood of connections between unconnected nodes based on similarity scores. This study explores the intersection of Large Language Models (LLMs) and Graph Learning, with a particular focus on Link Prediction tasks on Homogeneous Networks, where we are using LLMs to analyze social network structures and predict missing links. There have been several studies that leveraged LLMs for Knowledge Graphs, Heterogeneous Graphs, and Text-Attributed Graphs. However, leveraging LLMs for Homogeneous Graphs with no textual information is still an understudied area, which is what we aimed to explore. We developed a framework that leverages LLMs for link prediction tasks requiring no textual information with different learning strategies. Our results demonstrate improvement in model performance for predicting missing links, especially when provided with few examples or fine-tuned on the domain-specific datasets, achieving results on par with state-of-the-art results, even with no fine-tuning.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it