Progressive Monitoring of Generative Model Training Evolution
This addresses the need for early issue detection in complex generative models to optimize resources and reduce undesirable outcomes, representing an incremental improvement in training monitoring.
The paper tackles the problem of biases and inefficiencies in deep generative model training by introducing a progressive analysis framework for monitoring training evolution, which enables early detection and mitigation of issues, improving generated data quality.
While deep generative models (DGMs) have gained popularity, their susceptibility to biases and other inefficiencies that lead to undesirable outcomes remains an issue. With their growing complexity, there is a critical need for early detection of issues to achieve desired results and optimize resources. Hence, we introduce a progressive analysis framework to monitor the training process of DGMs. Our method utilizes dimensionality reduction techniques to facilitate the inspection of latent representations, the generated and real distributions, and their evolution across training iterations. This monitoring allows us to pause and fix the training method if the representations or distributions progress undesirably. This approach allows for the analysis of a models' training dynamics and the timely identification of biases and failures, minimizing computational loads. We demonstrate how our method supports identifying and mitigating biases early in training a Generative Adversarial Network (GAN) and improving the quality of the generated data distribution.