Variational Continual Learning

By Cuong V Nguyen, Yingzhen Li, Thang D. Bui, Richard E. Turner. 2017

811 citations recorded by the source corpus.

This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The framework can successfully train both deep discriminative models and deep generative models in complex continual learning settings where existing tasks evolve over time and entirely new tasks emerge. Experimental results show that VCL outperforms state-of-the-art continual learning methods on a variety of tasks, avoiding catastrophic forgetting in a fully automatic way.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Toward Understanding Catastrophic Forgetting in Continual Learning (2019, methodology): “Similar constructions can also be applied to the not-MNIST set [7], the fashion MNIST set [48], or the CIFAR set [23] such as in the split not-MNIST [29] and split CIFAR benchmarks [51].”
Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines (2018, background): “This evaluation scenario is widely adopted [3, 4, 5, 6, 7, 8, 9], despite criticism that it is less challenging in terms of forgetting [10].”
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes (2019, neutral): “Figure 6 (right) shows average results at the final task comparing to SI [41], EWC [43], VCL [44], and Riemannian Walk [42].”
How To Backdoor Federated Learning (2018, neutral): “With continuous training [33, 49], converged models are updated by participants throughout their deployment.”
A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, methodology): “Here we use VCL [55] as an example, which minimizes the following objective (i.e., maximize its negative): (7) where the KL-divergence can be computed in a closed-form and serves as an implicit regularization term.”
Decentralized Bayesian Learning over Graphs (2019, positive): “For all the experiments we choose Q to be the family of Gaussian mean-ﬁeld approximate posterior distributions with pdf given by G ( θ , µ , Σ ) , where Σ is a strictly diagonal matrix [10, 9].”
DisCoRL: Continual Reinforcement Learning via Policy Distillation (2019, methodology): “The ﬁrst method, referred to as rehearsal , keeps samples from previous tasks [Rebufﬁ et al., 2017, Nguyen et al., 2017].”
Continual and Multi-Task Architecture Search (2019, methodology): “Others proposed copying the previous task and augmenting with new task’s features (Rusu et al., 2016), intelligent synapses to accumulate task-related information (Zenke et al., 2017), or online variational inference (Nguyen et al., 2017).”
Getting a CLUE: A Method for Explaining Uncertainty Estimates (2020, methodology): “It enables the former to be used for uncertainty aware tasks, such as OOD detection (Daxberger & Hernández-Lobato, 2019), continual learning (Nguyen et al., 2018), active learning (Depeweg et al., 2018), and Bayesian optimization (Springenberg et al., 2016).”
Progress & Compress: A scalable framework for continual learning (2018, background): “A large body of literature recognises the importance of the continual learning problem, and there has been some increased interest in the topic recently (e.g. Rusu et al., 2016a; Shin et al., 2017; Lopez-Paz et al., 2017; Nguyen et al., 2017; Kirkpatrick et al., 2017; Chaudhry et al., 2018).”
Continual Learning via Sequential Function-Space Variational Inference (2023, background): “Variational continual learning ( VCL ; Nguyen et al., 2018; Swaroop et al., 2019), which extends the concept of online variational inference (Broderick et al., 2013; Ghahramani and Attias, 2000; Honkela and Valpola, 2003; Sato, 2001) to deep neural networks, uses the parameter covariance matrix of…”
Task-Free Continual Learning via Online Discrepancy Distance Learning (2022, neutral): “One of the most popular approaches to relieve forgetting is by imposing a regularization loss within the optimization procedure [7, 11, 13, 16, 19, 25, 26, 31, 34, 35, 40, 41, 57], where the network’s parameters which are important to the past tasks are penalized when updating.”
Class Gradient Projection For Continual Learning (2022, methodology): “Prevalent approaches to address the catastrophic forgetting problem in continual learning can be grouped into three broad categories: regularization-based approaches [2, 22, 30, 45], expansion-based approaches [17, 25, 31, 34, 36, 40], and memory-based approaches [3, 27, 33, 38].”
Disentangling Transfer in Continual Reinforcement Learning (2022, background): “Continual learning algorithms are often categorized into three classes: regularization-based e.g. [2, 23, 31], parameter isolation e.g. [26] and rehearsal methods e.g. [6, 7]; see also CL survey papers [8, 17, 32].”
Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions (2022, neutral): “Many works mitigate catastrophic forgetting during the learning process [37,14,48,68,31,42,20,2,10,3,64].”
Balancing Stability and Plasticity through Advanced Null Space in Continual Learning (2022, neutral): “Regularization-based methods can be divided into two classes: one is to distill knowledge from the previous model which is trained on the previous tasks [14, 15, 23, 36, 52, 59]; another is to explicitly use a regularizer to penalize the update of important parameters of previous tasks, preventing t”
Incremental Task Learning with Incremental Rank Updates (2022, methodology): “Incremental task learning is a subcategory of continual learning or lifelong learning approaches aim to address the problem of catastrophic forgetting by adapting the network or training process to learn new tasks without forgetting the previously learned ones [23,16,3,2,4,6,28,29,12].”
Improving Task-free Continual Learning by Distributionally Robust Memory Evolution (2022, methodology): “Most existing CL methods (Lopez-Paz & Ranzato, 2017; Nguyen et al., 2018; Kirkpatrick et al., 2017; Zenke et al., 2017; von Oswald et al., 2019; Wang et al., 2021; Saha et al., 2021; Pham et al., 2021; Wang et al., 2022) are only applicable to the task-aware setting, where there are clear task…”