{"type":"ScholarlyArticle","title":"Model Conversion via Differentially Private Data-Free Distillation","authors":[{"name":"Bochao Liu","slug":"bochao-liu","given":"Bochao","family":"Liu","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing 100085 , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing 100049 , China"},{"name":"Pengju Wang","slug":"pengju-wang","given":"Pengju","family":"Wang","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing 100085 , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing 100049 , China"},{"name":"Shikun Li","slug":"shikun-li","given":"Shikun","family":"Li","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing 100085 , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing 100049 , China"},{"name":"Dan Zeng","slug":"dan-zeng","given":"Dan","family":"Zeng","affiliation":"School of Communication and Information Engineering , Shanghai University , Shanghai 200444 , China"},{"name":"Shiming Ge","slug":"shiming-ge","given":"Shiming","family":"Ge","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing 100085 , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing 100049 , China"}],"abstract":"While massive valuable deep models trained on large-scale data have been released to facilitate the artificial intelligence community, they may encounter attacks in deployment which leads to privacy leakage of training data. In this work, we propose a learning approach termed differentially private data-free distillation (DPDFD) for model conversion that can convert a pretrained model (teacher) into its privacy-preserving counterpart (student) via an intermediate generator without access to training data. The learning collaborates three parties in a unified way. First, massive synthetic data are generated with the generator. Then, they are fed into the teacher and student to compute differentially private gradients by normalizing the gradients and adding noise before performing descent. Finally, the student is updated with these differentially private gradients and the generator is updated by taking the student as a fixed discriminator in an alternate manner. In addition to a privacy-preserving student, the generator can generate synthetic data in a differentially private way for other down-stream tasks. We theoretically prove that our approach can guarantee differential privacy and well convergence. Extensive experiments that significantly outperform other differentially private generative approaches demonstrate the effectiveness of our approach.","doi":"10.24963/ijcai.2023/243","url":"https://ijcai.org/proceedings/2023/243","pdf":"https://ijcai.org/proceedings/2023/0243.pdf","markdown":"https://ijcai.org/proceedings/2023/243.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/243","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Data Mining","track":"Main Track","number":243,"pages":{"first":2187,"last":2195},"keywords":["Computer Vision: CV: Bias, fairness and privacy","Data Mining: DM: Privacy-preserving data mining"],"videos":[],"references":[{"position":1,"raw":"[Abadi et al., 2016] Martin Abadi, Andy Chu, Ian Goodfel- low, et al. Deep learning with differential privacy. In CCS, pages 308-318, 2016.","title":"Deep learning with differential privacy","authors":"Martin Abadi, Andy Chu, Ian Goodfellow","year":"2016","venue":"CCS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Allen-Zhu, 2017] Z Natasha Allen-Zhu. Natasha 2: Faster non-convex optimization than sgd. arXiv:1708.08694, 2017.","title":"Natasha 2: Faster non-convex optimization than sgd","authors":"Allen-Zhu ;, Natasha Allen-Zhu","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bottou et al., 2018] Léon Bottou, Frank E Curtis, and Jorge Nocedal. Optimization methods for large-scale machine learning. SIAM Review, 60(2):223-311, 2018.","title":"Optimization methods for large-scale machine learning","authors":"Bottou","year":"2018","venue":"SIAM Review","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bu et al., 2022] Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, and George Karypis. Automatic clipping: Differen- tially private deep learning made easier and stronger. arXiv:2206.07136, 2022.","title":"Automatic clipping: Differentially private deep learning made easier and stronger","authors":"Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, George Karypis","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cao et al., 2021] Tianshi Cao, Alex Bie, Arash Vahdat, Sanja Fidler, and Karsten Kreis. Don't generate me: Train- ing differentially private generative models with sinkhorn divergence. In NeurIPS, pages 12480-12492, 2021.","title":"Don't generate me: Training differentially private generative models with sinkhorn divergence","authors":"Cao","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2019] Hanting Chen, Yunhe Wang, Chang Xu, Zhaohui Yang, Chuanjian Liu, Boxin Shi, Chunjing Xu, Chao Xu, and Qi Tian. Data-free learning of student net- works. In ICCV, pages 3514-3522, 2019.","title":"Data-free learning of student networks","authors":"Hanting Chen, Yunhe Wang, Chang Xu, Zhaohui Yang, Chuanjian Liu, Boxin Shi, Chunjing Xu, Chao Xu, Qi Tian","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chen et al., 2020] Dingfan Chen, Tribhuvanesh Orekondy, and Mario Fritz. Gs-wgan: A gradient-sanitized approach for learning differentially private generators. In NeurIPS, pages 12673-12684, 2020.","title":"Mario Fritz. Gs-wgan: A gradient-sanitized approach for learning differentially private generators","authors":"Chen","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chen et al., 2022] Jia-Wei Chen, Chia-Mu Yu, Ching-Chia Kao, Tzai-Wei Pang, and Chun-Shien Lu. Dpgen: Differ- entially private generative energy-guided network for nat- ural image synthesis. In CVPR, pages 8387-8396, 2022.","title":"Dpgen: Differentially private generative energy-guided network for natural image synthesis","authors":"Jia-Wei Chen, Chia-Mu Yu, Ching-Chia Kao, Tzai-Wei Pang, Chun-Shien Lu","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Choi et al., 2020] Yoojin Choi, Jihwan Choi, Mostafa El- Khamy, and Lee Jungwon. Data-free network quantization with adversarial knowledge distillation. In CVPR Work- shop, pages 710-711, 2020.","title":"Data-free network quantization with adversarial knowledge distillation","authors":"Yoojin Choi, Jihwan Choi, Mostafa El-Khamy, Lee Jungwon","year":"2020","venue":"CVPR Workshop","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Deng and Zhang, 2021] Xiang Deng and Zhongfei Zhang. Graph-free knowledge distillation for graph neural net- works. arXiv:2105.07519, 2021.","title":"Graph-free knowledge distillation for graph neural networks","authors":"Xiang Deng, Zhongfei Zhang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2021/320"},{"position":11,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR, pages 248-255, 2009.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Dosovitskiy et al., 2020] Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Min- derer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. An image is worth 16x16 words: Trans- formers for image recognition at scale. In ICLR, 2020.","title":"An image is worth 16x16 words: Transformers for image recognition at scale","authors":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Dwork and Roth, 2014] Cynthia Dwork and Aaron Roth. The algorithmic foundations of differential privacy. FTTCS, pages 211-407, 2014.","title":"The algorithmic foundations of differential privacy","authors":"Roth ; Dwork, Cynthia Dwork, Aaron Roth","year":"2014","venue":"FTTCS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Dwork et al., 2006] Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith. Calibrating noise to sensitivity in private data analysis. In TCC, pages 265-284, 2006.","title":"Calibrating noise to sensitivity in private data analysis","authors":"Cynthia Dwork, Frank Mcsherry, Kobbi Nissim, Adam Smith","year":"2006","venue":"TCC","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Fang et al., 2022] Gongfan Fang, Kanya Mo, Xinchao Wang, Jie Song, Shitao Bei, Haofei Zhang, and Mingli Song. Up to 100x faster data-free knowledge distillation. In AAAI, pages 6597-6604, 2022.","title":"Up to 100x faster data-free knowledge distillation","authors":"Fang","year":"2022","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Fredrikson et al., 2015] Matt Fredrikson, Somesh Jha, and Thomas Ristenpart. Model inversion attacks that exploit confidence information and basic countermeasures. In CCS, pages 1322-1333, 2015.","title":"Model inversion attacks that exploit confidence information and basic countermeasures","authors":"Matt Fredrikson, Somesh Jha, Thomas Ristenpart","year":"2015","venue":"CCS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ge et al., 2023] Shiming Ge, Bochao Liu, Pengju Wang, Yong Li, and Dan Zeng. Learning privacy-preserving student networks via discriminative-generative distillation. IEEE TIP, 32:116-127, 2023.","title":"Learning privacy-preserving student networks via discriminative-generative distillation","authors":"Shiming Ge, Bochao Liu, Pengju Wang, Yong Li, Dan Zeng","year":"2023","venue":"IEEE TIP","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ghadimi and Lan, 2013] Saeed Ghadimi and Guanghui Lan. Stochastic first-and zeroth-order methods for non- convex stochastic programming. SIAM Journal on Opti- mization, 23(4):2341-2368, 2013.","title":"Stochastic first-and zeroth-order methods for nonconvex stochastic programming","authors":"Saeed Ghadimi, Guanghui Lan","year":"2013","venue":"SIAM Journal on Optimization","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Goodfellow et al., 2014] Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial nets. In NeurIPS, pages 2672-2680, 2014.","title":"Generative adversarial nets","authors":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio","year":"2014","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Harder et al., 2021] Frederik Harder, Kamil Adamczewski, and Mijung Park. Dp-merf: Differentially private mean embeddings with random features for practical privacy- preserving data generation. In AISTATS, pages 1819- 1827, 2021.","title":"Dp-merf: Differentially private mean embeddings with random features for practical privacypreserving data generation","authors":"Frederik Harder, Kamil Adamczewski, Mijung Park","year":"2021","venue":"AISTATS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Howard et al., 2017] Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. Mo- bilenets: Efficient convolutional neural networks for mo- bile vision applications. arXiv:1704.04861, 2017.","title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","authors":"Menglong Andrew G Howard, Bo Zhu, Dmitry Chen, Weijun Kalenichenko, Tobias Wang, Marco Weyand, Hartwig Andreetto, Adam","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Huang et al., 2016] Gao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, and Kilian Q Weinberger. Deep networks with stochastic depth. In ECCV, pages 646-661, 2016.","title":"Deep networks with stochastic depth","authors":"Gao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, Kilian Q Weinberger","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Jia et al., 2019a] Ruoxi Jia, David Dao, Boxin Wang, Frances Ann Hubis, Nezihe Merve Gurel, Bo Li, Ce Zhang, Costas J Spanos, and Dawn Song. Effi- cient task-specific data valuation for nearest neighbor al- gorithms. Proc. VLDB Endow, pages 1610-1623, 2019.","title":"Efficient task-specific data valuation for nearest neighbor algorithms","authors":"Jia","year":"2019","venue":"Proc. VLDB Endow","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Jia et al., 2019b] Ruoxi Jia, David Dao, Boxin Wang, Frances Ann Hubis, Nick Hynes, Nezihe Merve Gürel, Bo Li, Ce Zhang, Dawn Song, and Costas J Spanos. To- wards efficient data valuation based on the shapley value. In AISTATS, pages 1167-1176, 2019.","title":"Towards efficient data valuation based on the shapley value","authors":"Jia","year":"2019","venue":"AISTATS","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Jordon et al., 2019] James Jordon, Jinsung Yoon, and Mi- haela Van Der Schaar. Pate-gan: Generating synthetic data with differential privacy guarantees. In ICLR, 2019.","title":"Pate-gan: Generating synthetic data with differential privacy guarantees","authors":"James Jordon, Jinsung Yoon, Mihaela Van, Der Schaar","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In NeurIPS, pages 1097- 1105, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton","year":"2012","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Krizhevsky, 2009] Alex Krizhevsky. Learning multiple lay- ers of features from tiny images. Technical report, Univer- sity of Toronto, 2009.","title":"Learning multiple layers of features from tiny images","authors":"Alex Krizhevsky","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[LeCun et al., 1998] Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning ap- plied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, 1998.","title":"Gradient-based learning applied to document recognition","authors":"Yann Lecun, Léon Bottou, Yoshua Bengio, Patrick Haffner","year":"1998","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Liu et al., 2015] Ziwei Liu, Ping Luo, Xiaogang Wang, and Tang Xiaoou. Deep learning face attributes in the wild. In ICCV, pages 3730-3738, 2015.","title":"Deep learning face attributes in the wild","authors":"Ziwei Liu, Ping Luo, Xiaogang Wang, Tang Xiaoou","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Long et al., 2021] Yunhui Long, Boxin Wang, Zhuolin Yang, Bhavya Kailkhura, Aston Zhang, Carl Gunter, and Bo Li. G-pate: Scalable differentially private data gener- ator via private aggregation of teacher discriminators. In NeurIPS, pages 2965-2977, 2021.","title":"G-pate: Scalable differentially private data generator via private aggregation of teacher discriminators","authors":"Yunhui Long, Boxin Wang, Zhuolin Yang, Bhavya Kailkhura, Aston Zhang, Carl Gunter, Bo Li","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Lopes et al., 2017] Raphael Lopes, Stefano Fenu, and Thad Starner. Data-free knowledge distillation for deep neural networks. arXiv:1710.07535, 2017.","title":"Data-free knowledge distillation for deep neural networks","authors":"Raphael Lopes, Stefano Fenu, Thad Starner","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[McMahan et al., 2018] H Brendan McMahan, Galen An- drew, Ulfar Erlingsson, Steve Chien, Ilya Mironov, Nico- las Papernot, and Peter Kairouz. A general approach to adding differential privacy to iterative training procedures. arXiv:1812.06210, 2018.","title":"A general approach to adding differential privacy to iterative training procedures","authors":"Galen H Brendan Mcmahan, Ulfar Andrew, Steve Erlingsson, Ilya Chien, Nicolas Mironov, Peter Papernot, Kairouz","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Mironov, 2017] Ilya Mironov. Rényi differential privacy. In CSF, pages 263-275, 2017.","title":"Rényi differential privacy","authors":"Ilya Mironov, Mironov","year":"2017","venue":"CSF","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Papernot et al., 2017] Nicolas Papernot, Martín Abadi, Ul- far Erlingsson, Ian Goodfellow, and Kunal Talwar. Semi- supervised knowledge transfer for deep learning from pri- vate training data. In ICLR, 2017.","title":"Semisupervised knowledge transfer for deep learning from private training data","authors":"Nicolas Papernot, Martín Abadi, Ulfar Erlingsson, Ian Goodfellow, Kunal Talwar","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Papernot et al., 2018] Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, and Úlfar Erlingsson. Scalable private learning with pate. In ICLR, 2018.","title":"Scalable private learning with pate","authors":"Nicolas Papernot, Shuang Song, Ilya Mironov, Kunal Ananth Raghunathan, Úlfar Talwar, Erlingsson","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Papernot et al., 2021] Nicolas Papernot, Abhradeep Thakurta, Shuang Song, Steve Chien, and Úlfar Erlings- son. Tempered sigmoid activations for deep learning with differential privacy. In AAAI, pages 9312-9321, 2021.","title":"Tempered sigmoid activations for deep learning with differential privacy","authors":"Nicolas Papernot, Abhradeep Thakurta, Shuang Song, Steve Chien, Úlfar Erlingsson","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Simonyan and Zisserman, 2015] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR, 2015.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Srinivas and Babu, 2015] Suraj Srinivas and R Venkatesh Babu. Data-free parameter pruning for deep neural net- works. arXiv:1507.06149, 2015.","title":"Data-free parameter pruning for deep neural networks","authors":"Suraj Srinivas, R Venkatesh, Babu","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Szegedy et al., 2015] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabi- novich. Going deeper with convolutions. In CVPR, pages 1-9, 2015.","title":"Going deeper with convolutions","authors":"Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Takagi et al., 2021] Shun Takagi, Tsubasa Takahashi, Yang Cao, and Masatoshi Yoshikawa. P3gm: Private high- dimensional data release via privacy preserving phased generative model. In ICDE, pages 169-180, 2021.","title":"P3gm: Private highdimensional data release via privacy preserving phased generative model","authors":"Takagi","year":"2021","venue":"ICDE","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Wang et al., 2021] Boxin Wang, Fan Wu, Yunhui Long, Luka Rimanic, Ce Zhang, and Bo Li. Datalens: Scalable privacy preserving training via gradient compression and aggregation. In CCS, pages 2146-2168, 2021.","title":"Datalens: Scalable privacy preserving training via gradient compression and aggregation","authors":"Boxin Wang, Fan Wu, Yunhui Long, Luka Rimanic, Ce Zhang, Bo Li","year":"2021","venue":"CCS","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Xiao et al., 2017] Han Xiao, Kashif Rasul, and Roland Vollgraf. Fashion-mnist: A novel image dataset for bench- marking machine learning algorithms. arXiv:1708.07747, 2017.","title":"Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms","authors":"Han Xiao, Kashif Rasul, Roland Vollgraf","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Xie et al., 2018] Liyang Xie, Kaixiang Lin, Shu Wang, Fei Wang, and Jiayu Zhou. Differentially private generative adversarial network. arXiv:1802.06739, 2018.","title":"Differentially private generative adversarial network","authors":"Xie","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Yang et al., 2019] Ziqi Yang, Jiyi Zhang, Ee-Chien Chang, and Zhenkai Liang. Neural network inversion in adversar- ial setting via background knowledge alignment. In CCS, pages 225-240, 2019.","title":"Neural network inversion in adversarial setting via background knowledge alignment","authors":"Ziqi Yang, Jiyi Zhang, Ee-Chien Chang, Zhenkai Liang","year":"2019","venue":"CCS","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Yang et al., 2021] Jiancheng Yang, Rui Shi, Donglai Wei, Zequan Liu, Lin Zhao, Bilian Ke, Hanspeter Pfister, and Bingbing Ni. Medmnist v2: A large-scale lightweight benchmark for 2d and 3d biomedical image classification. arXiv:2110.14795, 2021.","title":"Medmnist v2: A large-scale lightweight benchmark for 2d and 3d biomedical image classification","authors":"Jiancheng Yang, Rui Shi, Donglai Wei, Zequan Liu, Lin Zhao, Bilian Ke, Hanspeter Pfister, Bingbing Ni","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Ye et al., 2020] Yunan Ye, Hengzhi Pei, Boxin Wang, Pin- Yu Chen, Yada Zhu, Ju Xiao, and Bo Li. Reinforcement- learning based portfolio management with augmented as- set movement prediction states. In AAAI, pages 1112- 1119, 2020.","title":"Reinforcementlearning based portfolio management with augmented asset movement prediction states","authors":"Yunan Ye, Hengzhi Pei, Boxin Wang, Pin-Yu Chen, Yada Zhu, Ju Xiao, Bo Li","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Zagoruyko and Komodakis, 2017] Sergey Zagoruyko and Nikos Komodakis. Wide residual networks. In CVPR, 2017.","title":"Wide residual networks","authors":"Sergey Zagoruyko, Nikos Komodakis","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Zhang et al., 2018] Xiangyu Zhang, Xinyu Zhou, Mengx- iao Lin, and Jian Sun. Shufflenet: An extremely effi- cient convolutional neural network for mobile devices. In CVPR, pages 6848-6856, 2018.","title":"Shufflenet: An extremely efficient convolutional neural network for mobile devices","authors":"Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Zhao et al., 2022] Borui Zhao, Quan Cui, Renjie Song, Yiyu Qiu, and Jiajun Liang. Decoupled knowledge dis- tillation. In CVPR, pages 11953-11962, 2022.","title":"Decoupled knowledge distillation","authors":"Borui Zhao, Quan Cui, Renjie Song, Yiyu Qiu, Jiajun Liang","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Zhu et al., 2021] Zhuangdi Zhu, Junyuan Hong, and Jiayu Zhou. Data-free knowledge distillation for heterogeneous federated learning. In ICML, pages 12878-12889, 2021.","title":"Data-free knowledge distillation for heterogeneous federated learning","authors":"Zhu","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}