133 citations · 221 across the 11 of their papers we have counts for
11 papers
Information Flow Control in Machine Learning through Modular Model Architecture
Trishita Tiwari, Suchin Gururangan, Chuan Guo +7
In today's machine learning (ML) models, any part of the training data can affect the model output. This lack of control for information flow from training data to model output is…
Structured Pruning is All You Need for Pruning CNNs at Initialization
Yaohui Cai, Weizhe Hua, Hongzheng Chen +3
Pruning is a popular technique for reducing the model size and computational cost of convolutional neural networks (CNNs). However, a slow retraining or fine-tuning procedure is of…
Transformer Quality in Linear Time
Weizhe Hua, Zihang Dai, Hanxiao Liu +1
We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling long sequences. First, we propose a simple layer named gated attention un…
Sinan: Data Driven Resource Management for Cloud Microservices
Yanqi Zhang, Weizhe Hua, Zhuangzhuang Zhou +2
Cloud applications are increasingly shifting to interactive and loosely-coupled microservices. Despite their advantages, microservices complicate resource management, due to inter-…
BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining
Weizhe Hua, Yichi Zhang, Chuan Guo +2
Neural network robustness has become a central topic in machine learning in recent years. Most training algorithms that improve the model's robustness to adversarial and common cor…
Sinan: Data-Driven, QoS-Aware Cluster Management for Microservices
Yanqi Zhang, Weizhe Hua, Zhuangzhuang Zhou +2
Cloud applications are increasingly shifting from large monolithic services, to large numbers of loosely-coupled, specialized microservices. Despite their advantages in terms of fa…
Contrastive Weight Regularization for Large Minibatch SGD
Qiwei Yuan, Weizhe Hua, Yi Zhou +1
The minibatch stochastic gradient descent method (SGD) is widely applied in deep learning due to its efficiency and scalability that enable training deep networks with a large volu…
GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learning
Weizhe Hua, Muhammad Umar, Zhiru Zhang +1
This paper proposes GuardNN, a secure DNN accelerator that provides hardware-based protection for user data and model parameters even in an untrusted environment. GuardNN shows tha…
MGX: Near-Zero Overhead Memory Protection for Data-Intensive Accelerators
Weizhe Hua, Muhammad Umar, Zhiru Zhang +1
This paper introduces MGX, a near-zero overhead memory protection scheme for hardware accelerators. MGX minimizes the performance overhead of off-chip memory encryption and integri…
Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations
Yichi Zhang, Ritchie Zhao, Weizhe Hua +3
We propose precision gating (PG), an end-to-end trainable dynamic dual-precision quantization technique for deep neural networks. PG computes most features in a low precision and o…
Channel Gating Neural Networks
Weizhe Hua, Yuan Zhou, Christopher De Sa +2
This paper introduces channel gating, a dynamic, fine-grained, and hardware-efficient pruning scheme to reduce the computation cost for convolutional neural networks (CNNs). Channe…