Robust Generative Restricted Kernel Machines using Weighted Conjugate Feature Duality
This addresses the issue of data contamination in generative models for researchers and practitioners, but it is incremental as it builds on existing RKM frameworks with robust statistical methods.
The paper tackles the problem of training generative models on contaminated data, where outliers cause noisy generated images, by introducing weighted conjugate feature duality in Restricted Kernel Machines (RKMs) to robustly fine-tune the latent space, resulting in the generation of clean images and preservation of uncorrelated feature learning as shown in experiments on standard datasets.
Interest in generative models has grown tremendously in the past decade. However, their training performance can be adversely affected by contamination, where outliers are encoded in the representation of the model. This results in the generation of noisy data. In this paper, we introduce weighted conjugate feature duality in the framework of Restricted Kernel Machines (RKMs). The RKM formulation allows for an easy integration of methods from classical robust statistics. This formulation is used to fine-tune the latent space of generative RKMs using a weighting function based on the Minimum Covariance Determinant, which is a highly robust estimator of multivariate location and scatter. Experiments show that the weighted RKM is capable of generating clean images when contamination is present in the training data. We further show that the robust method also preserves uncorrelated feature learning through qualitative and quantitative experiments on standard datasets.