Online continual learning with no task boundaries

By Rahaf Aljundi, Min Lin, Baptiste Goujaud, Yoshua Bengio. 2019

45 citations recorded by the source corpus.

How researchers see this paper

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

In Meta & Continual Learning

Citations in the corpus

Online Continual Learning Via Candidates Voting (2021, methodology): “Dataset: We use Split CIFAR-10 [4], Split CIFAR100 [44] and CORE-50 [28] for evaluation in this part.”
Continual Learning in Low-rank Orthogonal Subspaces (2020, neutral): “In other approaches [Lopez-Paz and Ranzato, 2017, Chaudhry et al., 2019a, Aljundi et al., 2019] the episodic memory is used as an optimization constraint that discourages increases in loss at past tasks.”
Linear Mode Connectivity in Multitask and Continual Learning (2020, background): “It also aims to work in scenarios where task boundaries are not well defined or provided, or when the data distribution shifts slowly or when a multi-task solution does not exist (Rao et al., 2019; Aljundi et al., 2019; He et al., 2019; Kaplanis et al., 2019).”
Understanding the Role of Training Regimes in Continual Learning (2020, methodology): “Continual Learning as an emerging field in Artificial Intelligence is connected to many other areas such as Meta Learning [4, 35, 24, 62], Few Shot Learning [75, 20], Multi-task and Transfer Learning [24, 35] and the closely related problem of exploring task boundary or task detection [60, 2, 25, 36”
Using Hindsight to Anchor Past Knowledge in Continual Learning (2019, background): “In other approaches (Lopez-Paz & Ranzato, 2017; Chaudhry et al., 2019a; Aljundi et al., 2019b) the episodic memory is used as an optimization constraint that discour-ages increases in loss at past tasks.”
Continual learning: A comparative study on how to defy forgetting in classification tasks (2019, methodology): “Parameter isolation-based methods Note that our categorization overlaps to some extent with that introduced in [27], [43].”
Task Agnostic Continual Learning via Meta Learning (2019, methodology): “Only recently, the CL community started to look at the task agnostic setting (Zeno et al., 2018; Aljundi et al., 2019).”
Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting (2020, unknown): “learning the new task (Rebuffi et al., 2017; Shin et al., 2017; Lopez-Paz and Ranzato, 2017; Aljundi et al., 2019).”
Online Learned Continual Compression with Stacked Quantization Module (2019, methodology): “…learning (Thrun & Mitchell, 1995), which has for now largely focused on classiﬁcation, approaches based on storing memories for later use have emerged as some of the most effective in online settings (Lopez-Paz et al., 2017; Aljundi et al., 2018; Chaudhry et al.; 2019; Aljundi et al., 2019).”
Not Just Selection, but Exploration: Online Class-Incremental Continual Learning via Dual View Consistency (2022, background): “Following recent continual learning literature [2,4,5,35, 45], we consider a supervised online class-incremental continual learning setting, where a model needs to learn new classes continually from an online data stream (the samples in the data stream can be seen only once).”
Learning with Long-term Remembering: Following the Lead of Mixed Stochastic Gradient (2019, methodology): “In (Aljundi et al., 2019), a line of methods are proposed to select important samples to store in the memory in order to reduce memory size.”
A Continual Learning Survey: Defying Forgetting in Classification Tasks (2019, methodology): “Note that our categorization overlaps to some extent with that introduced in previous work [26], [48].”
Online Learned Continual Compression with Adaptive Quantization Modules (2019, methodology): “…learning (Thrun & Mitchell, 1995), which has for now largely focused on classiﬁcation, approaches based on storing memories for later use have emerged as some of the most effective in online settings (Lopez-Paz et al., 2017; Aljundi et al., 2018; Chaudhry et al.; 2019; Aljundi et al., 2019).”
Streaming Graph Neural Networks via Continual Learning (2020, background): “[2] and [3] both propose methods that extend continual learning to online setting on streaming data, which are based on regularization and replay respectively.”
Continual Learning in Neural Networks (2019, methodology): “This work was published as an article in NeurIPS 2019 [9].”