Unifying Importance Based Regularisation Methods for Continual Learning

34 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.

A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “Interest-ingly, these importance measurements have been shown to be all tantamount to an approximation of the FIM [107], although stemming from different motivations.”
Incorporating neuro-inspired adaptability for continual learning in artificial intelligence (2023, methodology): “In particular, since the loss functions of such methods [7–10] typically have a similar form and differ only in the metric for estimating the parameter importance [49] (Method 4.”
Continual Learning by Modeling Intra-Class Variation (2022, neutral): “Hence, some recent work (Kirkpatrick et al., 2017; Aljundi et al., 2018; Zenke et al., 2017; Benzing, 2022) explores different measurements of the parameter importance.”
Class-Incremental Learning: A Survey (2023, background): “[189] shows that despite stemming from very different motivations, both SI [74] and MAS [75] approximate the square root of the Fisher Information, with the Fisher being the theoretically justified basis of EWC.”