Wujie Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wujie Sun has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Chun Chen
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
3 shared publicationsDefang Chen
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
3 shared publicationsYan Feng
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
3 shared publicationsCan Wang
Zhejiang University
2 shared publications- Can Wang
State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou, China
2 shared publications Deshi Ye
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
2 shared publications
Latest Publications
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6898-6908
TopKGAT: A Top-K Objective-Driven Architecture for Recommendation
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 6898-6908
Open AccessTopKGAT: A Top-K Objective-Driven Architecture for Recommendation
- 1 April 2024
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 25 (4) , 585-599
Multi-exit self-distillation with appropriate teachers
Multi-exit architecture allows early-stop inference to reduce computational cost, which can be used in resource-constrained circumstances. Recent works com
- 1 April 2024
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 25 (4) , 585-599
Multi-exit self-distillation with appropriate teachers
Multi-exit architecture allows early-stop inference to reduce computational cost, which can be used in resource-constrained circumstances. Recent works com
- Open Access
Knowledge Translation: A New Pathway for Model Compression
Deep learning has witnessed significant advancements in recent years at the cost of increasing training, inference, and model storage overhead. While existing model compression methods strive to reduce the number of model parameters while maintaining high accuracy, they inevitably necessitate the re-training of the compressed model or impose architectural constraints. To overcome these limitations, this paper presents a novel framework, termed \textbf{K}nowledge \textbf{T}ranslation (KT), wherein a ``translation'' model is trained to receive the parameters of a larger model and generate compressed parameters. The concept of KT draws inspiration from language translation, which effectively employs neural networks to convert different languages, maintaining identical meaning. Accordingly, we explore the potential of neural networks to convert models of disparate sizes, while preserving their functionality. We propose a comprehensive framework for KT, introduce data augmentation strategies to enhance model performance despite restricted training data, and successfully demonstrate the feasibility of KT on the MNIST dataset. Code is available at \url{https://github.com/zju-SWJ/KT}.
Open AccessKnowledge Translation: A New Pathway for Model Compression
Deep learning has witnessed significant advancements in recent years at the cost of increasing training, inference, and model storage overhead. While existing model compression methods strive to reduce the number of model parameters while maintaining high accuracy, they inevitably necessitate the re-training of the compressed model or impose architectural constraints. To overcome these limitations, this paper presents a novel framework, termed \textbf{K}nowledge \textbf{T}ranslation (KT), wherein a ``translation'' model is trained to receive the parameters of a larger model and generate compressed parameters. The concept of KT draws inspiration from language translation, which effectively employs neural networks to convert different languages, maintaining identical meaning. Accordingly, we explore the potential of neural networks to convert models of disparate sizes, while preserving their functionality. We propose a comprehensive framework for KT, introduce data augmentation strategies to enhance model performance despite restricted training data, and successfully demonstrate the feasibility of KT on the MNIST dataset. Code is available at \url{https://github.com/zju-SWJ/KT}.
- Open Access
- 1 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 810-815
Accelerating Diffusion Sampling with Classifier-based Feature Distillation
Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively aligning output images of N-step teacher sampler with N/2-step student sampler. In this paper, we argue that this distillation-based accelerating method can be further improved, especially for few-step samplers, with our proposed Classifier-based Feature Distillation (CFD). Instead of aligning output images, we distill teacher’s sharpened feature distribution into the student with a dataset-independent classifier, making the student focus on those important features to improve performance. We also introduce a dataset-oriented loss to further optimize the model. Experiments on CIFAR-10 show the superiority of our method in achieving high quality and fast sampling. Code is available at https://github.com/zju-SWJ/RCFD.
- 1 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 810-815
Open AccessAccelerating Diffusion Sampling with Classifier-based Feature Distillation
Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively aligning output images of N-step teacher sampler with N/2-step student sampler. In this paper, we argue that this distillation-based accelerating method can be further improved, especially for few-step samplers, with our proposed Classifier-based Feature Distillation (CFD). Instead of aligning output images, we distill teacher’s sharpened feature distribution into the student with a dataset-independent classifier, making the student focus on those important features to improve performance. We also introduce a dataset-oriented loss to further optimize the model. Experiments on CIFAR-10 show the superiority of our method in achieving high quality and fast sampling. Code is available at https://github.com/zju-SWJ/RCFD.
- Open Access
Accelerating Diffusion Sampling with Classifier-based Feature Distillation
Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively aligning output images of $N$-step teacher sampler with $N/2$-step student sampler. In this paper, we argue that this distillation-based accelerating method can be further improved, especially for few-step samplers, with our proposed \textbf{C}lassifier-based \textbf{F}eature \textbf{D}istillation (CFD). Instead of aligning output images, we distill teacher's sharpened feature distribution into the student with a dataset-independent classifier, making the student focus on those important features to improve performance. We also introduce a dataset-oriented loss to further optimize the model. Experiments on CIFAR-10 show the superiority of our method in achieving high quality and fast sampling. Code is provided at \url{https://github.com/zju-SWJ/RCFD}.
Open AccessAccelerating Diffusion Sampling with Classifier-based Feature Distillation
Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively aligning output images of $N$-step teacher sampler with $N/2$-step student sampler. In this paper, we argue that this distillation-based accelerating method can be further improved, especially for few-step samplers, with our proposed \textbf{C}lassifier-based \textbf{F}eature \textbf{D}istillation (CFD). Instead of aligning output images, we distill teacher's sharpened feature distribution into the student with a dataset-independent classifier, making the student focus on those important features to improve performance. We also introduce a dataset-oriented loss to further optimize the model. Experiments on CIFAR-10 show the superiority of our method in achieving high quality and fast sampling. Code is provided at \url{https://github.com/zju-SWJ/RCFD}.