paper-with-me

Papers

Variational Continual Bayesian Meta-Learning

2021-12-01 · NeurIPS 2021 12 · Qiang Zhang, Jinyuan Fang, Zaiqiao Meng, Shangsong Liang, Emine Yilmaz

Conventional meta-learning considers a set of tasks from a stationary distribution. In contrast, this paper focuses on a more complex online setting, where tasks arrive sequentially and follow a non-stationary distribution. Accordingly, we propose a Variational Continual Bayesian Meta-Learning (VC-BML) algorithm. VC-BML maintains a Dynamic Gaussian Mixture Model for meta-parameters, with the number of component distributions determined by a Chinese Restaurant Process. Dynamic mixtures at the meta-parameter level increase the capability to adapt to diverse tasks due to a larger parameter space, alleviating the negative knowledge transfer problem. To infer posteriors of model parameters, compared to the previously used point estimation method, we develop a more robust posterior approximation method -- structured variational inference for the sake of avoiding forgetting knowledge. Experiments on tasks from non-stationary distributions show that VC-BML is superior in transferring knowledge among diverse tasks and alleviating catastrophic forgetting in an online setting.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-LearningTransfer LearningVariational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Statistical mechanics of continual learning: variational principle and mean-field potential

2022-12-06 · Chan Li, Zhenye Huang, Wenxuan Zou, Haiping Huang

An obstacle to artificial general intelligence is set by continual learning of multiple tasks of different nature. Recently, various heuristic tricks, both from machine learning and from neuroscience angles, were propose…

Continual LearningMulti-Task Learning

Improving and Understanding Variational Continual Learning

2019-05-06 · Siddharth Swaroop, Cuong V. Nguyen, Thang D. Bui, Richard E. Turner

In the continual learning setting, tasks are encountered sequentially. The goal is to learn whilst i) avoiding catastrophic forgetting, ii) efficiently using model capacity, and iii) employing forward and backward transf…

Continual LearningPermuted-MNISTSplit-MNISTTransfer Learning

Continual Learning from the Perspective of Compression

2020-06-26 · ICML Workshop LifelongML 2020 7 · Xu He, Min Lin

Connectionist models such as neural networks suffer from catastrophic forgetting. In this work, we study this problem from the perspective of information theory and define forgetting as the increase of description length…

Continual Learning

Variational Bayes: A report on approaches and applications

2019-05-26 · Manikanta Srikar Yellapragada, Chandra Prakash Konkimalla

Deep neural networks have achieved impressive results on a wide variety of tasks. However, quantifying uncertainty in the network's output is a challenging task. Bayesian models offer a mathematical framework to reason a…

Bayesian InferenceContinual Learningreinforcement-learningReinforcement Learning+2

Learning to Continually Learn with the Bayesian Principle

2024-05-29 · Soochan Lee, Hyeonseong Jeon, Jaehyeon Son, Gunhee Kim

In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other…

Continual LearningMeta-Learning