Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization

By Hung-Jen Chen, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun. 2020

50 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

A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “InstAParam [272] selects and consolidates appropriate network paths for individual training samples.”
Balancing Stability and Plasticity through Advanced Null Space in Continual Learning (2022, methodology): “We compare the proposed method against competitive and wellestablished methods(4), including 5 regularization-based methods using importance measure (EWC [17], MAS [1], MUC-MAS [25], SI [58], and CPR [5]), 2 regularization-based methods using knowledge distillation (LwF [23] and GDWILD [20]), 1 arch”
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima (2021, background): “Incremental learning focuses on the challenging problem of continually learning to recognize new classes in new coming data without forgetting old classes [6, 7, 10, 51].”
Towards Better Plasticity-Stability Trade-off in Incremental Learning: A Simple Linear Connector (2021, neutral): “We compare our method with EWC [21], MAS [2] , MUC-MAS [26], SI [44], LwF [25], InstAParam [5], GD-WILD [23], GEM [27], A-GEM [4], MEGA [16], OWM [43] and Adam-NSCL [37].”
New Insights on Reducing Abrupt Representation Change in Online Continual Learning (2021, methodology): “(2018); van de Ven & Tolias (2019); Normandin et al. (2021); Lesort et al.”
Few-Shot Incremental Learning with Continually Evolved Classifiers (2021, background): “Incremental learning (IL) is an active machine learning task that aims to learn new knowledge continually without forgetting [3, 4, 7, 25].”
How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition (2022, methodology): “Recently, similar ideas have achieved compositional generalization by directly learning rules over fixed symbols (Nye et al., 2020) or by providing a curriculum (Chen et al., 2020b).”