Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural Network Pruning

no code implementations • 8 Apr 2023 • Shanglin Zhou, Mikhail A. Bragin, Lynn Pepin, Deniz Gurevin, Fei Miao, Caiwen Ding

We evaluate our method on image classification tasks using CIFAR-10 and ImageNet with state-of-the-art MLP-Mixer, Swin Transformer, and VGG-16, ResNet-18, ResNet-50 and ResNet-110, MobileNetV2.

Image Classification Lane Detection +4

Towards Real-Time Temporal Graph Learning

1 code implementation • 8 Oct 2022 • Deniz Gurevin, Mohsin Shan, Tong Geng, Weiwen Jiang, Caiwen Ding, Omer Khan

Prior work operates on pre-collected temporal graph data and is not designed to handle updates on a graph in real-time.

graph construction Graph Learning +3

Towards Sparsification of Graph Neural Networks

1 code implementation • 11 Sep 2022 • Hongwu Peng, Deniz Gurevin, Shaoyi Huang, Tong Geng, Weiwen Jiang, Omer Khan, Caiwen Ding

In this paper, we utilize two state-of-the-art model compression methods (1) train and prune and (2) sparse training for the sparsification of weight layers in GNNs.

Image Classification Link Prediction +4

Enabling Retrain-free Deep Neural Network Pruning using Surrogate Lagrangian Relaxation

no code implementations • 18 Dec 2020 • Deniz Gurevin, Shanglin Zhou, Lynn Pepin, Bingbing Li, Mikhail Bragin, Caiwen Ding, Fei Miao

We further accelerate the convergence of the SLR by using quadratic penalties.

Image Classification Lane Detection +4

Beware the Black-Box: on the Robustness of Recent Defenses to Adversarial Examples

1 code implementation • 18 Jun 2020 • Kaleel Mahmood, Deniz Gurevin, Marten van Dijk, Phuong Ha Nguyen

We provide this large scale study and analyses to motivate the field to move towards the development of more robust black-box defenses.