Combined Group and Exclusive Sparsity for Deep Neural Networks

151 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.

Continual Learning with Node-Importance based Adaptive Group Sparse Regularization (2020, methodology): “The group Lasso [40] regularization, which was favorably used in model compression [4, 37, 38, 29], has been also adopted for continual learning in [39].”
Adaptive Group Sparse Regularization for Continual Learning (2020, methodology): “Since identifying important nodes while training a neural network model is exactly what is done in the group Lassobased model compression methods [33, 3, 34, 26], we adopt the same methodology for compactly identifying important nodes when continuously learning new tasks.”
Learning Intrinsic Sparse Structures within Long Short-term Memory (2017, methodology): “Group Lasso based methods were proved to be effective to reduce coarse-grain structures ( e.g., neurons, ﬁlters, channels, ﬁlter shapes, and even layers) in CNNs (Wen et al. (2016), Alvarez & Salzmann (2016), Lebedev & Lempitsky (2016), Yoon & Hwang (2017)).”