HeuGAT: Integrating Heuristic and Graph Attention Network for Improved Link Prediction and Breakup Prediction in Social Network Structures
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
Social networks are composed of diverse interactions that can generally be classified as positive (e.g., friendships, likes) or negative (e.g., conflict, dislikes). While link prediction, anticipating the formation of new ties, has been widely explored. Predicting link breakups, where existing ties weaken or dissolve, remains relatively understudied. These transitions are often subtle and gradual, frequently going undetected until negative outcomes have already occurred. Current systems rely heavily on user manual intervention to flag such changes, making them both inefficient and reactive. In this study, we address the challenge of automatically predicting potential link breakups by analyzing both structural and behavioral cues within social network graphs. Building upon the ClassReg heuristic, we introduce HeuGAT, an enhanced approach that replaces the original deep learning layer with a Graph Attention Network (GAT) layer. This integration allows the model to more effectively capture the contextual significance of neighboring nodes through attention mechanisms. Our results demonstrate the value of GNNbased models in advancing link prediction and breakup prediction for more resilient social network ecosystems.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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