Gradient Based Memory Editing for Task-Free Continual Learning

By Xisen Jin, Arka Sadhu, Junyi Du, Xiang Ren. 2020

31 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 on Class Incremental Blurry Task Configuration with Anytime Inference (2021, neutral): “Note that task-free and class-incremental are compatible (Jin et al., 2020; van de Ven et al., 2021).”
Rainbow Memory: Continual Learning with a Memory of Diverse Samples (2021, background): “Many previous works have been evaluated either of online [13, 1, 23] or ofﬂine [48, 39, 5, 4] setup, while GDumb [38] reports on both of setups.”
Online Continual Learning in Image Classification: An Empirical Survey (2021, neutral): “3 3 3 3 GDumb[23], DER[58], MER[59] CBRS[60], GMED[61], PRS[62]”
GDumb: A Simple Approach that Questions Our Progress in Continual Learning (2020, methodology): “We present results in Table 4 and show that GDumb outperforms parallel works like HAL [35], QMED [12], ARM [41] in addition to outperforming recent works GSS [37], MIR [11], and ADI [47], consistently across datasets.”
An Investigation of Replay-based Approaches for Continual Learning (2021, background): “least the works of [42]–[45] provide benchmarks on disjoint MNIST (split MNIST) and disjoint CIFAR10 (split CIFAR10).”
Memory-efficient Reinforcement Learning with Knowledge Consolidation (2022, methodology): “Concretely, these methods retain knowledge explicitly by storing previous training samples (Rebufﬁ et al. 2017, Riemer et al. 2018, Hayes et al. 2019, Aljundi et al. 2019a, Chaudhry et al. 2019, Jin et al. 2020).”
TAG: Task-based Accumulated Gradients for Lifelong learning (2021, methodology): “Replay-based methods maintain an ‘episodic memory’, containing a few examples from past tasks, that is revisited while learning a new task [46, 26].”