AutoGAN: An Automated Human-Out-of-the-Loop Approach for Training Generative Adversarial 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
Generative Adversarial Networks (GANs) have been used for many applications with overwhelming success. The training process of these models is complex, involving a zero-sum game between two neural networks trained in an adversarial manner. Thus, to use GANs, researchers and developers need to answer the question: “Is the GAN sufficiently trained?”. However, understanding when a GAN is well trained for a given problem is a challenging and laborious task that usually requires monitoring the training process and human intervention for assessing the quality of the GAN generated outcomes. Currently, there is no automatic mechanism for determining the required number of epochs that correspond to a well-trained GAN, allowing the training process to be safely stopped. In this paper, we propose AutoGAN, an algorithm that allows one to answer this question in a fully automatic manner with minimal human intervention, being applicable to different data modalities including imagery and tabular data. Through an extensive set of experiments, we show the clear advantage of our solution when compared against alternative methods, for a task where the GAN outputs are used as an oversampling method. Moreover, we show that AutoGAN not only determines a good stopping point for training the GAN, but it also allows one to run fewer training epochs to achieve a similar or better performance with the GAN outputs.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 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