Sheng Lin — accepted AI-conference papers

2021

A Secure and Efficient Federated Learning Framework for NLP

Chenghong Wang, Jieren Deng, Xianrui Meng, Yijue Wang, Ji Li, Sheng Lin +4

EMNLP 2021main

In this work, we consider the problem of designing secure and efficient federated learning (FL) frameworks for NLP. Existing solutions under this literature either consider a trusted aggregator or require heavy-weight cryptographic primitives, which makes the performance significantly degraded. More…

Cited by 24 Source ↗PDF ↗Scholar ↗

2020

An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices

Xiaolong Ma, Wei Niu, Tianyun Zhang, Sijia Liu, Sheng Lin, Hongjia Li +6

ECCV 2020poster

Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms. However, most of the pruning techniques are essentially trade-offs between model accuracy and regularity w…

Cited by 30 Source ↗PDF ↗code ↗Scholar ↗