ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models
It addresses the problem of model interpretability for researchers and engineers in industry, though it is incremental as it builds on existing visual tools.
The paper tackles the challenge of understanding complex, industry-scale deep neural network models by developing ActiVis, an interactive visualization system that enables exploration at instance- and subset-levels, which has been deployed on Facebook's machine learning platform.
While deep learning models have achieved state-of-the-art accuracies for many prediction tasks, understanding these models remains a challenge. Despite the recent interest in developing visual tools to help users interpret deep learning models, the complexity and wide variety of models deployed in industry, and the large-scale datasets that they used, pose unique design challenges that are inadequately addressed by existing work. Through participatory design sessions with over 15 researchers and engineers at Facebook, we have developed, deployed, and iteratively improved ActiVis, an interactive visualization system for interpreting large-scale deep learning models and results. By tightly integrating multiple coordinated views, such as a computation graph overview of the model architecture, and a neuron activation view for pattern discovery and comparison, users can explore complex deep neural network models at both the instance- and subset-level. ActiVis has been deployed on Facebook's machine learning platform. We present case studies with Facebook researchers and engineers, and usage scenarios of how ActiVis may work with different models.