GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
This addresses computational efficiency for researchers and practitioners using GPs in incremental few-shot learning, though it appears incremental as it builds on existing GP and deep kernel learning methods.
The paper tackles the computational challenges of Gaussian processes (GPs) in large datasets by proposing GP-Tree, a tree-based hierarchical model for multi-class classification with deep kernel learning, which scales well with classes and data size and achieves improved accuracy on incremental few-shot learning benchmarks.
Gaussian processes (GPs) are non-parametric, flexible, models that work well in many tasks. Combining GPs with deep learning methods via deep kernel learning (DKL) is especially compelling due to the strong representational power induced by the network. However, inference in GPs, whether with or without DKL, can be computationally challenging on large datasets. Here, we propose GP-Tree, a novel method for multi-class classification with Gaussian processes and DKL. We develop a tree-based hierarchical model in which each internal node of the tree fits a GP to the data using the Pólya Gamma augmentation scheme. As a result, our method scales well with both the number of classes and data size. We demonstrate the effectiveness of our method against other Gaussian process training baselines, and we show how our general GP approach achieves improved accuracy on standard incremental few-shot learning benchmarks.