Pruning Adversarially Robust Neural Networks without Adversarial Examples

1 code implementation • 9 Oct 2022 • Tong Jian, Zifeng Wang, Yanzhi Wang, Jennifer Dy, Stratis Ioannidis

Adversarial pruning compresses models while preserving robustness.

Adversarial Robustness

SparCL: Sparse Continual Learning on the Edge

1 code implementation • 20 Sep 2022 • Zifeng Wang, Zheng Zhan, Yifan Gong, Geng Yuan, Wei Niu, Tong Jian, Bin Ren, Stratis Ioannidis, Yanzhi Wang, Jennifer Dy

SparCL achieves both training acceleration and accuracy preservation through the synergy of three aspects: weight sparsity, data efficiency, and gradient sparsity.

Continual Learning

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

1 code implementation • 12 Jan 2022 • Batool Salehi, Guillem Reus-Muns, Debashri Roy, Zifeng Wang, Tong Jian, Jennifer Dy, Stratis Ioannidis, Kaushik Chowdhury

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 within short contact times.

Edge-computing

Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness

1 code implementation • NeurIPS 2021 • Zifeng Wang, Tong Jian, Aria Masoomi, Stratis Ioannidis, Jennifer Dy

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

Adversarial Robustness

Learn-Prune-Share for Lifelong Learning

1 code implementation • 13 Dec 2020 • Zifeng Wang, Tong Jian, Kaushik Chowdhury, Yanzhi Wang, Jennifer Dy, Stratis Ioannidis

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.