Scalable Recollections for Continual Lifelong Learning

Riemer, Matthew; Klinger, Tim; Bouneffouf, Djallel; Franceschini, Michele

doi:10.1609/aaai.v33i01.33011352

Cited by 42 publications

(26 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, more training data usually means lower training efficiency. These challenges could be alleviated by optimizing data storage methods [ 99 ], but it still cannot be completely overcome. If the memory capacity is limited [ 17 ], the sample size of a single knowledge category will gradually decrease with the accumulation of tasks, and its impact on the model will gradually decrease.…”

Section: Discussion and Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

An Appraisal of Incremental Learning Methods

Luo

Yin

Bai

et al. 2020

Entropy

View full text Add to dashboard Cite

As a special case of machine learning, incremental learning can acquire useful knowledge from incoming data continuously while it does not need to access the original data. It is expected to have the ability of memorization and it is regarded as one of the ultimate goals of artificial intelligence technology. However, incremental learning remains a long term challenge. Modern deep neural network models achieve outstanding performance on stationary data distributions with batch training. This restriction leads to catastrophic forgetting for incremental learning scenarios since the distribution of incoming data is unknown and has a highly different probability from the old data. Therefore, a model must be both plastic to acquire new knowledge and stable to consolidate existing knowledge. This review aims to draw a systematic review of the state of the art of incremental learning methods. Published reports are selected from Web of Science, IEEEXplore, and DBLP databases up to May 2020. Each paper is reviewed according to the types: architectural strategy, regularization strategy and rehearsal and pseudo-rehearsal strategy. We compare and discuss different methods. Moreover, the development trend and research focus are given. It is concluded that incremental learning is still a hot research area and will be for a long period. More attention should be paid to the exploration of both biological systems and computational models.

show abstract

Section: Discussion and Comparisonmentioning

confidence: 99%

“…Guo et al [ 98 ] proposed an example set exemplar-based subspace clustering method. Riemer et al [ 99 ] used an autoencoder based model to support scalable data storage and retrieval for scalable old data.…”

Section: Methods Descriptionmentioning

confidence: 99%

An Appraisal of Incremental Learning Methods

Luo

Yin

Bai

et al. 2020

Entropy

View full text Add to dashboard Cite

show abstract

“…Instead of storing raw samples as exemplars, Shin et al (2017); Riemer et al (2019) generate "pseudo'' samples akin to past data. The NLG model itself can generate pseudo exemplars.…”

Section: B1 Comparison To Pseudo Exemplar Replaymentioning

confidence: 99%

Continual Learning for Natural Language Generation in Task-oriented Dialog Systems

Mi¹,

Chen²,

Zhao³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

Natural language generation (NLG) is an essential component of task-oriented dialog systems. Despite the recent success of neural approaches for NLG, they are typically developed in an offline manner for particular domains. To better fit real-life applications where new data come in a stream, we study NLG in a "continual learning" setting to expand its knowledge to new domains or functionalities incrementally. The major challenge towards this goal is catastrophic forgetting, meaning that a continually trained model tends to forget the knowledge it has learned before. To this end, we propose a method called ARPER (Adaptively Regularized Prioritized Exemplar Replay) by replaying prioritized historical exemplars, together with an adaptive regularization technique based on Elastic Weight Consolidation. Extensive experiments to continually learn new domains and intents are conducted on MultiWoZ-2.0 to benchmark ARPER with a wide range of techniques. Empirical results demonstrate that ARPER significantly outperforms other methods by effectively mitigating the detrimental catastrophic forgetting issue.

show abstract

“…A few methods reduce this storage requirement by storing a compressed representation of the data, including Lifelong Generative Modeling (Ramapuram et al, 2017 ), FearNet (Kemker and Kanan, 2018 ), Deep Generative Replay (Shin et al, 2017 ), and Expert Gates (Aljundi et al, 2017 ). Some methods specifically use autoencoders for this task (Zhou et al, 2012 ; Riemer et al, 2017 ; Parisi et al, 2018b ). However, even when compressed, data requires significantly more parameters to store than parametric networks.…”

Section: Prior Workmentioning

confidence: 99%

Self-Net: Lifelong Learning via Continual Self-Modeling

Mandivarapu¹,

Camp²,

Estrada³

2020

Front. Artif. Intell.

View full text Add to dashboard Cite

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence. While recent approaches achieve some degree of CL in deep neural networks, they either (1) store a new network (or an equivalent number of parameters) for each new task, (2) store training data from previous tasks, or (3) restrict the network's ability to learn new tasks. To address these issues, we propose a novel framework, Self-Net, that uses an autoencoder to learn a set of low-dimensional representations of the weights learned for different tasks. We demonstrate that these low-dimensional vectors can then be used to generate high-fidelity recollections of the original weights. Self-Net can incorporate new tasks over time with little retraining, minimal loss in performance for older tasks, and without storing prior training data. We show that our technique achieves over 10X storage compression in a continual fashion, and that it outperforms state-of-the-art approaches on numerous datasets, including continual versions of MNIST, CIFAR10, CIFAR100, Atari, and task-incremental CORe50. To the best of our knowledge, we are the first to use autoencoders to sequentially encode sets of network weights to enable continual learning.

show abstract

Scalable Recollections for Continual Lifelong Learning

Cited by 42 publications

References 29 publications

An Appraisal of Incremental Learning Methods

An Appraisal of Incremental Learning Methods

Continual Learning for Natural Language Generation in Task-oriented Dialog Systems

Self-Net: Lifelong Learning via Continual Self-Modeling

Contact Info

Product

Resources

About