# Bayesian Few-Shot Classification with One-vs-Each P'olya-Gamma Augmented Gaussian Processes

arXiv: https://arxiv.org/abs/2007.10417 · HTML: https://mlsanity.com/paper/2007.10417/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 30 of 32)

- [Personalized Federated Learning with Gaussian Processes](https://mlsanity.com/paper/2106.15482/) (2021)
- [GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning](https://mlsanity.com/paper/2102.07868/) (2021)
- [HyperShot: Few-Shot Learning by Kernel HyperNetworks](https://mlsanity.com/paper/2203.11378/) (2022)
- [Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation](https://mlsanity.com/paper/2208.00306/) (2022)
- [Bayesian Federated Learning: A Survey](https://mlsanity.com/paper/2304.13267/) (2023)
- [Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction](https://mlsanity.com/paper/2205.02708/) (2022)
- [Few-Shot Learning with Class Imbalance](https://mlsanity.com/paper/2101.02523/) (2021)
- [Dense Gaussian Processes for Few-Shot Segmentation](https://mlsanity.com/paper/2110.03674/) (2021)
- [HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks](https://mlsanity.com/paper/2205.15745/) (2022)
- [Non-Gaussian Gaussian Processes for Few-Shot Regression](https://mlsanity.com/paper/2110.13561/) (2021)
- [Revisiting Local Descriptor for Improved Few-Shot Classification](https://mlsanity.com/paper/2103.16009/) (2021)
- [Transductive Decoupled Variational Inference for Few-Shot Classification](https://mlsanity.com/paper/2208.10559/) (2022)
- [Guided Deep Kernel Learning](https://mlsanity.com/paper/2302.09574/) (2023)
- [Revisiting Logistic-softmax Likelihood in Bayesian Meta-Learning for Few-Shot Classification](https://mlsanity.com/paper/2310.10379/) (2023)
- [Uncertainty-Aware Semi-Supervised Few Shot Segmentation](https://mlsanity.com/paper/2110.08954/) (2021)
- [PatchMix Augmentation to Identify Causal Features in Few-shot Learning](https://mlsanity.com/paper/2211.16019/) (2022)
- [Heterogeneous Multi-Task Gaussian Cox Processes](https://mlsanity.com/paper/2308.15364/) (2023)
- [Bayesian Principles Improve Prompt Learning In Vision-Language Models](https://mlsanity.com/paper/2504.14123/) (2025)
- [Functional Ensemble Distillation](https://mlsanity.com/paper/2206.02183/) (2022)
- [Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spaces](https://mlsanity.com/paper/2311.05088/) (2023)
- [MetaKernel: Learning Variational Random Features with Limited Labels](https://mlsanity.com/paper/2105.03781/) (2021)
- [Meta-free few-shot learning via representation learning with weight averaging](https://mlsanity.com/paper/2204.12466/) (2022)
- [Bayesian Personalized Federated Learning with Shared and Personalized Uncertainty Representations](https://mlsanity.com/paper/2309.15499/) (2023)
- [Deep Gaussian Processes for Few-Shot Segmentation](https://mlsanity.com/paper/2103.16549/) (2021)
- [How Sensitive are Meta-Learners to Dataset Imbalance?](https://mlsanity.com/paper/2104.05344/) (2021)
- [Bayesian Evidential Learning for Few-Shot Classification](https://mlsanity.com/paper/2207.13137/) (2022)
- [Accelerating Convergence in Bayesian Few-Shot Classification](https://mlsanity.com/paper/2405.01507/) (2024)
- [Task Diversity in Bayesian Federated Learning: Simultaneous Processing of Classification and Regression](https://mlsanity.com/paper/2412.10897/) (2024)
- [Hypernetwork approach to Bayesian MAML](https://mlsanity.com/paper/2210.02796/) (2022)
- [On the Calibration and Uncertainty with P'olya-Gamma Augmentation for Dialog Retrieval Models](https://mlsanity.com/paper/2303.08606/) (2023)

## Abstract (arXiv)

Few-shot classification (FSC), the task of adapting a classifier to unseen classes given a small labeled dataset, is an important step on the path toward human-like machine learning. Bayesian methods are well-suited to tackling the fundamental issue of overfitting in the few-shot scenario because they allow practitioners to specify prior beliefs and update those beliefs in light of observed data. Contemporary approaches to Bayesian few-shot classification maintain a posterior distribution over model parameters, which is slow and requires storage that scales with model size. Instead, we propose a Gaussian process classifier based on a novel combination of P'olya-Gamma augmentation and the one-vs-each softmax approximation that allows us to efficiently marginalize over functions rather than model parameters. We demonstrate improved accuracy and uncertainty quantification on both standard few-shot classification benchmarks and few-shot domain transfer tasks.