Di Gao

Di Gao

Auto-generated profile, based on publicly available information

Di Gao

College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2020 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
DGDi Gao
Di Gao
DRDayane Reis
Dayane Reis
XHXiaobo Sharon Hu
Xiaobo Sharon Hu
CZCheng Zhuo
Cheng Zhuo

3 March 2021 in IEEE Design & Test
Verified
Journal Article
Closed access
QHQingrong Huang
Qingrong Huang
DRDayane Reis
Dayane Reis
CLChao Li
Chao Li
DGDi Gao
Di Gao
MNMichael Niemier
Michael Niemier
CZCheng Zhuo
Cheng Zhuo
The article presents computing-in-memory designs using ferroelectric field-effect transistors. Thanks to good support for various key logic operations, these designs can be used for multiple learning tasks/paradigms, from classical machine learning to hyperdimensional computing, and achieve both compactness and efficiency.

17 October 2022 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
DGDi Gao
Di Gao
ZYZeyu Yang
Zeyu Yang
QHQingrong Huang
Qingrong Huang
GZGrace Li Zhang
Grace Li Zhang
XYXunzhao Yin
Xunzhao Yin
CZCheng Zhuo
Cheng Zhuo
Memristor crossbar arrays are considered to be a promising platform for neuromorphic computing. To deploy a trained neural network model on memristor crossbars, memristors need to be programmed to the corresponding weight values. In fact, due to device based process variation and noise, deviations of the stored weights from the trained weights are inevitable, thereby causing the degradation of the actual inference performance. This paper proposes a unified Bayesian inference based framework, BRoCoM, which connects device nonidealities and algorithmic training together for robust computing on memristor crossbars. BRoCoM is able to incorporate different levels of nonidealities into prior weight distribution, and transform robustness optimization to Bayesian neural network training, the weights of neural networks are optimized to accommodate uncertainties and minimize inference degradation. Experimental results confirm the capability of the proposed BRoCoM to achieve stable inference performance while tolerating the non-ideal effects of process variation and noise.

31 October 2022 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
CZCheng Zhuo
Cheng Zhuo
DGDi Gao
Di Gao
LLLiangwei Liu
Liangwei Liu
The deployment of deep learning applications has to address the increasing privacy concerns when using private and sensitive data for training. A conventional deep learning model is prone to privacy attacks that can recover the sensitive information from either model parameters or accesses to the inference model. Recently, differential privacy (DP) has been proposed to offer provable privacy guarantees by randomizing the training process of neural networks. However, many approaches tend to provide the worst case privacy protection for model publishing, inevitably impairing the accuracy of the trained models. Thus, we present a novel private knowledge transfer strategy, where the private teacher trained on sensitive data is not publicly accessible but the student models can be released with privacy guarantees. In this paper, a three-player (teacher-student-discriminator) learning framework, Private Knowledge Distillation with Generative Adversarial Networks (PKDGAN), is proposed, where the student acquires the distilled knowledge from the teacher and is trained with the discriminator to generate similar outputs as the teacher. Moreover, a cooperative learning strategy is also suggested to support the collective training of multiple students against the discriminator when each student is with insufficient unlabelled training data. To enforce rigorous privacy guarantees, PKDGAN applies a Rényi differential privacy mechanism throughout the training process, and use it with a moment accountant technique to track the privacy cost. PKDGAN allows students to be trained with unlabelled public data and very few epochs, which avoids the exposure of training data while ensuring model performance. In the experiments, PKDGAN is found to have consistently good performance on various datasets (MNIST, SVHN, CIFAR-10, and Market-1501). When compared to prior works [1], [2], PKDGAN exhibits 5-82% accuracy loss improvement without compromising any privacy guarantee.

11 October 2021 in IEEE Design & Test
Verified
Journal Article
Closed access
CZCheng Zhuo
Cheng Zhuo
DGDi Gao
Di Gao
YCYuan Cao
Yuan Cao
TSTianhao Shen
Tianhao Shen
LZLi Zhang
Li Zhang
XYXunzhao Yin
Xunzhao Yin
Dynamic voltage and frequency scaling (DVFS) is an essential approach to optimize the performance and energy tradeoff. In this article, learning models predict the workload and then estimate the corresponding power and thermal dissipation. The proposed framework utilizes a deep reinforcement learning (DRL)-based controller. —Ulf Schlichtmann, Technical University of Munich

7 May 2020 in Current Microbiology
Verified
Journal Article
Closed access
PDF file
YWYuxin Wang
Yuxin Wang
XYXiaomei Ye
Xiaomei Ye
XKXiangping Kong
Xiangping Kong
YXYonglan Xi
Yonglan Xi
JDJing Du
Jing Du
JHJian He
Jian He