Multi-view Generative Adversarial Networks
This work addresses a practical challenge in multi-view learning for scenarios with incomplete data, though it is incremental as it extends the BiGAN model.
The paper tackles the problem of learning from multi-view data with missing views by proposing Multi-view BiGAN (MV-BiGAN), which performs density estimation and updates predictions as views are added, demonstrating these capabilities in experiments across various datasets.
Learning over multi-view data is a challenging problem with strong practical applications. Most related studies focus on the classification point of view and assume that all the views are available at any time. We consider an extension of this framework in two directions. First, based on the BiGAN model, the Multi-view BiGAN (MV-BiGAN) is able to perform density estimation from multi-view inputs. Second, it can deal with missing views and is able to update its prediction when additional views are provided. We illustrate these properties on a set of experiments over different datasets.