# NPCL: Neural Processes for Uncertainty-Aware Continual Learning

arXiv: https://arxiv.org/abs/2310.19272 · HTML: https://mlsanity.com/paper/2310.19272/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 55 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [Conditional Neural Processes](https://mlsanity.com/paper/1807.01613/) (2018)
- [Ladder Variational Autoencoders](https://mlsanity.com/paper/1602.02282/) (2016)
- [Neural Processes](https://mlsanity.com/paper/1807.01622/) (2018)
- [Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1904.00310/) (2019)
- [DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion](https://mlsanity.com/paper/2111.11326/) (2021)
- [Attentive Neural Processes](https://mlsanity.com/paper/1901.05761/) (2019)
- [Class-Incremental Continual Learning into the eXtended DER-verse](https://mlsanity.com/paper/2201.00766/) (2022)
- [CARD: Classification and Regression Diffusion Models](https://mlsanity.com/paper/2206.07275/) (2022)
- [Measuring and regularizing networks in function space](https://mlsanity.com/paper/1805.08289/) (2018)
- [Continual Learning in Low-rank Orthogonal Subspaces](https://mlsanity.com/paper/2010.11635/) (2020)
- [Noisy Natural Gradient as Variational Inference](https://mlsanity.com/paper/1712.02390/) (2017)
- [Hierarchical VAEs Know What They Don't Know](https://mlsanity.com/paper/2102.08248/) (2021)
- [Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables](https://mlsanity.com/paper/2008.09469/) (2020)

## Built on by (most cited first, 14 of 14)

- [Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning](https://mlsanity.com/paper/2403.18886/) (2024)
- [CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models](https://mlsanity.com/paper/2403.19137/) (2024)
- [LADA: Scalable Label-Specific CLIP Adapter for Continual Learning](https://mlsanity.com/paper/2505.23271/) (2025)
- [Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'](https://mlsanity.com/paper/2505.04950/) (2025)
- [Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors](https://mlsanity.com/paper/2505.20680/) (2025)
- [Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts](https://mlsanity.com/paper/2506.21035/) (2025)
- [Mining Your Own Secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models](https://mlsanity.com/paper/2410.00700/) (2024)
- [Take Only What You Need: Rank Minimization as an Implicit Forgetting Regularizer in Continual Learning](https://mlsanity.com/paper/2412.01004/) (2024)
- [Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes](https://mlsanity.com/paper/2505.01726/) (2025)
- [R'enyi Neural Processes](https://mlsanity.com/paper/2405.15991/) (2024)
- [TinySubNets: An efficient and low capacity continual learning strategy](https://mlsanity.com/paper/2412.10869/) (2024)
- [Information-Theoretic Dual Memory System for Continual Learning](https://mlsanity.com/paper/2501.07382/) (2025)
- [Incrementally Learning Multiple Diverse Data Domains via Multi-Source Dynamic Expansion Model](https://mlsanity.com/paper/2501.08878/) (2025)
- [Continual learning via probabilistic exchangeable sequence modelling](https://mlsanity.com/paper/2503.20725/) (2025)

## Abstract (arXiv)

Continual learning (CL) aims to train deep neural networks efficiently on streaming data while limiting the forgetting caused by new tasks. However, learning transferable knowledge with less interference between tasks is difficult, and real-world deployment of CL models is limited by their inability to measure predictive uncertainties. To address these issues, we propose handling CL tasks with neural processes (NPs), a class of meta-learners that encode different tasks into probabilistic distributions over functions all while providing reliable uncertainty estimates. Specifically, we propose an NP-based CL approach (NPCL) with task-specific modules arranged in a hierarchical latent variable model. We tailor regularizers on the learned latent distributions to alleviate forgetting. The uncertainty estimation capabilities of the NPCL can also be used to handle the task head/module inference challenge in CL. Our experiments show that the NPCL outperforms previous CL approaches. We validate the effectiveness of uncertainty estimation in the NPCL for identifying novel data and evaluating instance-level model confidence. Code is available at urlhttps://github.com/srvCodes/NPCL.