activity
20202022
most citedSparCL: Sparse Continual Learning on the Edge

18 citations · 34 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG20221 cited

Pruning Adversarially Robust Neural Networks without Adversarial Examples

Tong Jian, Zifeng Wang, Yanzhi Wang +2

Adversarial pruning compresses models while preserving robustness. Current methods require access to adversarial examples during pruning. This significantly hampers training effici…

cs.LG202218 cited

SparCL: Sparse Continual Learning on the Edge

Zifeng Wang, Zheng Zhan, Yifan Gong +7

Existing work in continual learning (CL) focuses on mitigating catastrophic forgetting, i.e., model performance deterioration on past tasks when learning a new task. However, the t…

cs.LG20224 cited

Deep Learning on Multimodal Sensor Data at the Wireless Edge for Vehicular Network

Batool Salehi, Guillem Reus-Muns, Debashri Roy +5

Beam selection for millimeter-wave links in a vehicular scenario is a challenging problem, as an exhaustive search among all candidate beam pairs cannot be assuredly completed with…

cs.LG20218 cited

Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness

Zifeng Wang, Tong Jian, Aria Masoomi +2

We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier. In addition to the…

cs.LG20203 cited

Learn-Prune-Share for Lifelong Learning

Zifeng Wang, Tong Jian, Kaushik Chowdhury +3

In lifelong learning, we wish to maintain and update a model (e.g., a neural network classifier) in the presence of new classification tasks that arrive sequentially. In this paper…