Status-Aware Signed Heterogeneous Network Embedding With Graph Neural Networks
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
Many real-world applications are inherently modeled as signed heterogeneous networks or graphs with positive and negative links. Signed graph embedding embeds rich structural and semantic information of a signed graph into low-dimensional node representations. Existing methods usually exploit social structural balance theory to capture the semantics of the complex structure in a signed graph. These methods either omit the node features or may discard the direction information of the links. To address these issues, we propose a new framework, called a status-aware graph neural network (S-GNN), to boost the representation learning performance. S-GNN is equipped with a loss function designed based on status theory, a social-psychological theory specifically developed for directed signed graphs. Extensive experimental results on benchmarking datasets verified that S-GNN can distill comprehensive information ingrained in a signed graph in the embedding space. Specifically, S-GNN achieves state-of-the-art accuracy, robustness, and scalability: it speeds up the processing time of link sign prediction by up to$6.5 \times $and increases accuracy by up to 18.8% as compared with the alternatives. We also show that S-GNN can obtain effective status scores of nodes for link sign prediction and node ranking tasks, both of which yield state-of-the-art performance.
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 | 0.004 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.003 |
| 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