Improved Schemes for Episodic Memory-based Lifelong Learning

By Yunhui Guo, Mingrui Liu, Tianbao Yang, Tajana Šimunić. 2019

104 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

Beyond Not-Forgetting: Continual Learning with Backward Knowledge Transfer (2022, background): “, [3, 22, 8]) store and replay the old tasks data when learning the new task, while orthogonalprojection based methods (e.”
Balancing Stability and Plasticity through Advanced Null Space in Continual Learning (2022, methodology): “We use ResNet-18 [11] as the backbone [4,6,10,11].”
Incremental Prompting: Episodic Memory Prompt for Lifelong Event Detection (2022, background): “Though experience replay (Lopez-Paz and Ranzato, 2017; de Masson d’Autume et al., 2019; Guo et al., 2020; Han et al., 2020; Zhao et al., 2022) and knowledge distillation (Chuang et al.”
TRGP: Trust Region Gradient Projection for Continual Learning (2022, background): “Many approaches (e.g., (Rusu et al., 2016; Li & Hoiem, 2017; Dhar et al., 2019; Guo et al., 2020; Zeng et al., 2019)) have been proposed to address the forgetting issue, which can be generally divided into two classes depending on the network architecture, i.e., expansion methods and non-expansion…”
An Empirical Investigation of the Role of Pre-training in Lifelong Learning (2021, background): “, 2019); (2) memorybased approaches that augment the model with episodic memory for sparse experience replay of previous task examples, either during training (Lopez-Paz and Ranzato, 2017; Chaudhry et al., 2018b, 2019; Guo et al., 2020) and/ or during inference (Rebuffi et al.”
Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning (2021, methodology): “[12] proposes a unified view of episodic memory-based continual learning methods, including GEM and A-GEM, and improves performance over these methods by using a loss-balancing update scheme.”
Model Zoo: A Growing Brain That Learns Continually (2021, background): “…of continual learning techniques, e.g., episodic memory-based ones (Lopez-Paz and Ranzato, 2017; Chaudhry et al., 2019a; Farajtabar et al., 2020; Guo et al., 2020a), data replay (Robins, 1995; Shin et al., 2017; Lee et al., 2017), new architectures (Serra et al., 2018), generative replay-based…”
Same State, Different Task: Continual Reinforcement Learning without Interference (2021, background): “Or small samples from previous tasks (memories) [41, 24, 3, 16, 51].”
Rainbow Memory: Continual Learning with a Memory of Diverse Samples (2021, methodology): “However, those approaches overlook the importance of memory management and normally adopt simple random sampling [17, 2] or reservoir sampling [40] or ring-buffer sampling [7].”
Gradient Projection Memory for Continual Learning (2021, methodology): “Guo et al. (2020) propose a unified view of episodic memory-based CL methods, that include GEM and A-GEM and improves performance over these methods utilizing loss-balancing update rule.”
Gradient Surgery for Multi-Task Learning (2020, background): “Multiple approaches to continual learning have studied how to prevent gradient updates from adversely affecting previously-learned tasks through various forms of gradient projection [36, 7, 18, 23].”
Lifelong Generative Modelling Using Dynamic Expansion Graph Model (2021, methodology): “Other methods rely on memory systems such as using past learned data to guide the optimization (Chaudhry et al. 2018; Guo et al. 2020; Pan et al. 2020), using Generative Adversarial Nets (GANs) or VAEs (Achille et al.”
Continual Variational Autoencoder Learning via Online Cooperative Memorization (2022, methodology): “Additionally, existing methods using episodic memory [5, 9] can also be explained by using Eq.”
How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition (2022, methodology): “A similar work imposed invariance to partial permutations on a language understanding system (Guo et al., 2020a).”
SDDGR: Stable Diffusion-Based Deep Generative Replay for Class Incremental Object Detection (2024, methodology): “Among these, Replay methods are most frequently utilized for their simple yet powerful effects and can be categorized into two types: partial experience replay (ER) [2, 4, 14, 27, 44, 47] and generative replay (GR) [6, 12, 23, 58, 66, 67].”
Mitigating Catastrophic Forgetting in Online Continual Learning by Modeling Previous Task Interrelations via Pareto Optimization (2024, methodology): “…algorithms have been proposed in continual learning (CL) area, aiming to enhance the incremental learning ability of DNNs on streaming tasks (Lopez-Paz & Ranzato, 2017; Serra et al., 2018; Gupta et al., 2020; Guo et al., 2020; Arani et al., 2022; Wang et al., 2023; Chrysakis & Moens, 2023).”