Task-agnostic Continual Learning with Hybrid Probabilistic Models

By Polina Kirichenko, Mehrdad Farajtabar, Dushyant Rao, Balaji Lakshminarayanan, Nir Levine, Ang Li, Huiyi Hu, Andrew Gordon Wilson, Razvan Pascanu. 2021

24 citations recorded by the source corpus.

Learning new tasks continuously without forgetting on a constantly changing data distribution is essential for real-world problems but extremely challenging for modern deep learning. In this work we propose HCL, a Hybrid generative-discriminative approach to Continual Learning for classification. We model the distribution of each task and each class with a normalizing flow. The flow is used to learn the data distribution, perform classification, identify task changes, and avoid forgetting, all leveraging the invertibility and exact likelihood which are uniquely enabled by the normalizing flow model. We use the generative capabilities of the flow to avoid catastrophic forgetting through generative replay and a novel functional regularization technique. For task identification, we use state-of-the-art anomaly detection techniques based on measuring the typicality of the model's statistics. We demonstrate the strong performance of HCL on a range of continual learning benchmarks such as split-MNIST, split-CIFAR, and SVHN-MNIST.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Architecture Matters in Continual Learning (2022, background): “…Riemer et al., 2018) or incorporate them as part of the optimization process (e.g., gradient projection) (Farajtabar et al., 2020; Chaudhry et al., 2018; Balaji et al., 2020), or learn a generative model (Shin et al., 2017; Kirichenko et al., 2021) or kernel (Derakhshani et al., 2021) to do so.”
Wide Neural Networks Forget Less Catastrophically (2021, methodology): “Perhaps the strongest are the replay-based methods that store a small subset of data from previous tasks in the replay buffer, and either use it directly in the form of experience replay with new task (Shin et al., 2017; Kirichenko et al., 2021; Rolnick et al., 2019; Riemer et al., 2018; Chaudhry et”
Efficient Continual Learning Ensembles in Neural Network Subspaces (2022, background): “The second group of methods in continual learning is the memory-based methods that keep a small episodic memory of data from past tasks to either 2021), or train a generative model to serve that purpose (Shin et al., 2017; Kirichenko et al., 2021).”
VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty (2022, methodology): “Kirichenko et al. (2021) proposed using likelihood-based mixture models to handle the multi-modality of the different tasks.”