A continual learning survey: Defying forgetting in classification tasks

Abstract

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern (1) a taxonomy and extensive overview of the state-of-the-art; (2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner; (3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods and 4 baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time and storage.

Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks

“…We now evaluate B-CL by comparing it with both non-continual learning and continual learning baselines. We follow the standard CL evaluation method in (Lange et al, 2019). We first present B-CL a sequence of aspect sentiment classification (ASC) tasks for it to learn.…”

Unsupervised Model Personalization While Preserving Privacy and Scalability: An Open Problem

“…Further, sequentially learning multiple tasks by finetuning a neural network results in significant loss of previously acquired knowledge. Literature on continual learning largely addresses coping with this catastrophic forgetting [5,25]. Nonetheless, recent works mainly focus on supervised data, leaving the richness of available unsupervised user data unused.…”

“…Nonetheless, recent works mainly focus on supervised data, leaving the richness of available unsupervised user data unused. Following [5], these methods can be subdivided into three main categories. First, parameter-isolation methods preserve task knowledge by obtaining task-specific masks [22,21,31], or dynamically extending the architecture [30].…”

“…In this respect, even though the server presents a plausibly overfitted model, adaptation to the user domain remains efficacious with AdaBN-S. Furthermore, the effects of BN on continual learning methods still urge further elicitation, as it is mainly disregarded in current state-of-the-art [5,25].…”

Learning to Solve NLP Tasks in an Incremental Number of Languages

“…For example, in a real-world application, customers may request deletion of their data, or the service itself may provide specific data retention policies, or the adopted model may be provided by a third party that did not release the training data (Chen and Moschitti, 2019). In these cases, new language support can be added in a Continual Learning (CL) setting (Lange et al, 2019), that is fine-tuning the model only using the annotated material for the new language(s). However, this approach is vulnerable to the Catastrophic Forgetting (CF) (McCloskey and Cohen, 1989) of previously learned languages, a well-documented concern discussed in Chen et al (2018): when a model is incrementally fine-tuned on new data distributions, it risks forgetting how to treat instances of the previously learned ones.…”