Generating Labeled Graphs Using Conditional Wasserstein GANs
Bibliographic record
Abstract
Graph-structured data arises in many domains, from biological and chemical networks to social and knowledge graphs, where capturing both structural and class-specific patterns is critical. Generating realistic graphs conditioned on target class labels remains a challenging problem due to the discrete and irregular nature of graph topology. In this work, we propose a conditional Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) for labeled graph generation. Our framework integrates class information at both the generator and discriminator, enabling controllable synthesis of graphs with desired properties. The generator maps random noise vectors and class embeddings to node feature and adjacency representations, while the discriminator leverages a Graph Neural Network to jointly evaluate graph authenticity and class consistency. We evaluate the approach on benchmark graph datasets, demonstrating its ability to generate structurally coherent and classconsistent graphs. Experimental results show improved stability, highlighting the framework's potential for applications in synthetic dataset augmentation, controlled graph generation, and downstream tasks. This project's source code is publicly available at https://github.com/ava-12/Labeled_Wasserstein_GANs.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".