Shiwei Liu

发表

More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity

Xuxi Chen, Zhangyang Wang, Mykola Pechenizkiy, 2022, ICLR.

Selfish Sparse RNN Training pdf

Mykola Pechenizkiy, Decebal Constantin Mocanu, Yulong Pei, 2021, ICML.

Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers

Zhangyang Wang, Tianlong Chen, Zhenyu (Allen) Zhang, 2023, ICLR.

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

Zhangyang Wang, Mykola Pechenizkiy, D. Mocanu, 2021, NeurIPS.

Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training

Mykola Pechenizkiy, Decebal Constantin Mocanu, Lu Yin, 2021, ICML.

Ten Lessons We Have Learned in the New "Sparseland": A Short Handbook for Sparse Neural Network Researchers

Zhangyang Wang, Shiwei Liu, 2023, arXiv.org.

Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!

Zhangyang Wang, Tianlong Chen, Tianjin Huang, 2023, ICLR.

Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost

Mykola Pechenizkiy, Lu Yin, Tianjin Huang, 2022, AAAI.

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

Zhangyang Wang, Mykola Pechenizkiy, D. Mocanu, 2022, ICLR.

Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity

Zhangyang Wang, Mykola Pechenizkiy, D. Mocanu, 2021, ICLR.

Sparse evolutionary deep learning with over one million artificial neurons on commodity hardware

Mykola Pechenizkiy, Yulong Pei, Decebal Constantin Mocanu, 2019, Neural Computing and Applications.

Achieving Personalized Federated Learning with Sparse Local Models

Weiwei Lin, Li Shen, Shiwei Liu, 2022, ArXiv.

Dynamic Sparse Network for Time Series Classification: Learning What to "see"

Mykola Pechenizkiy, D. Mocanu, Yu Zhang, 2022, NeurIPS.

Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance

Li Shen, Tianlong Chen, Yuesong Tian, 2022, ArXiv.

Topological Insights in Sparse Neural Networks

Mykola Pechenizkiy, David L. Ferraro, D. Mocanu, 2020, ECML/PKDD.

The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter

Zhangyang Wang, Tianlong Chen, Ajay Jaiswal, 2023, ArXiv.

Ten Lessons We Have Learned in the New "Sparseland": A Short Handbook for Sparse Neural Network Researchers

Zhangyang Wang, Shiwei Liu, 2023, ArXiv.

Enhancing Adversarial Training via Reweighting Optimization Trajectory

Mykola Pechenizkiy, Tianlong Chen, Lu Yin, 2023, arXiv.org.

Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models

Zhangyang Wang, A. Jaiswal, Tianlong Chen, 2023, ICML.

Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication

Zhangyang Wang, A. Jaiswal, Tianlong Chen, 2023, 2306.10466.

FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity pdf

Mykola Pechenizkiy, Zhangyang Wang, Decebal Constantin Mocanu, 2021, ArXiv.

D EEP E NSEMBLING WITH N O O VERHEAD FOR EITHER T RAINING OR T ESTING : T HE A LL -R OUND B LESSINGS OF D YNAMIC S PARSITY

Zhangyang Wang, Mykola Pechenizkiy, D. Mocanu, 2022 .

Revisiting Pruning at Initialization Through the Lens of Ramanujan Graph

Zhangyang Wang, R. Marculescu, Shiwei Liu, 2023, ICLR.

R EVISITING P RUNING AT I NITIALIZATION THROUGH THE L ENS OF R AMANUJAN G RAPH

Zhangyang Wang, R. Marculescu, Shiwei Liu, 2023 .

Efficient and effective training of sparse recurrent neural networks

Mykola Pechenizkiy, Vlado Menkovski, Decebal Constantin Mocanu, 2021, Neural Computing and Applications.

Dynamic Sparsity Is Channel-Level Sparsity Learner

Zhangyang Wang, Mykola Pechenizkiy, Xiaolong Ma, 2023, ArXiv.

Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication

Zhangyang Wang, A. Jaiswal, Tianlong Chen, 2023, ICML.

Sparse evolutionary deep learning with over one million artificial neurons on commodity hardware

Mykola Pechenizkiy, D. Mocanu, Yulong Pei, 2019, Neural Computing and Applications.

The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter

Zhangyang Wang, Tianlong Chen, Ajay Jaiswal, 2023, ArXiv.

Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training

Mykola Pechenizkiy, Meng Fang, Vlado Menkovski, 2022, UAI.

Don’t Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance

Li Shen, Tianlong Chen, Yuesong Tian, 2022, International Journal of Computer Vision.

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

Mykola Pechenizkiy, Tianlong Chen, Yihua Zhang, 2023, ArXiv.

Enhancing Adversarial Training via Reweighting Optimization Trajectory

Mykola Pechenizkiy, Tianlong Chen, Lu Yin, 2023, ECML/PKDD.

Many-Task Federated Learning: A New Problem Setting and A Simple Baseline

R. Kompella, Myungjin Lee, Xiaohan Chen, 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

On improving deep learning generalization with adaptive sparse connectivity pdf

Decebal Constantin Mocanu, Mykola Pechenizkiy, Shiwei Liu, 2019, ArXiv.