{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:26:43Z","timestamp":1775597203461,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CNS-1955593"},{"name":"OAC-2126291"},{"name":"SES-2231874"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,6]]},"DOI":"10.1145\/3583740.3626620","type":"proceedings-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T18:35:50Z","timestamp":1723055750000},"page":"250-252","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Poster: Self-Supervised Quantization-Aware Knowledge Distillation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9432-673X","authenticated-orcid":false,"given":"Kaiqi","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University, Tempe, Arizona, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9133-1088","authenticated-orcid":false,"given":"Ming","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University, Tempe, Arizona, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,8,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Knowledge distillation via module replacing for automatic speech recognition with recurrent neural network transducer","author":"Zhao K.","year":"2022","unstructured":"K. Zhao, H. D. Nguyen, A. Jain, N. Susanj, A. Mouchtaris, L. Gupta, and M. Zhao, \"Knowledge distillation via module replacing for automatic speech recognition with recurrent neural network transducer,\" 2022."},{"key":"e_1_3_2_1_2_1","first-page":"1","volume-title":"Speech and Signal Processing (ICASSP)","author":"Zhao K.","year":"2023","unstructured":"K. Zhao, Y. Chen, and M. Zhao, \"A contrastive knowledge transfer framework for model compression and transfer learning,\" in ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1--5, IEEE, 2023."},{"key":"e_1_3_2_1_3_1","volume-title":"PMLR","author":"Zhao K.","year":"2023","unstructured":"K. Zhao, A. Jain, and M. Zhao, \"Automatic attention pruning: Improving and automating model pruning using attentions,\" in International Conference on Artificial Intelligence and Statistics, pp. 10470--10486, PMLR, 2023."},{"key":"e_1_3_2_1_4_1","volume-title":"Model compression as constrained optimization, with application to neural nets. part v: combining compressions,\" arXiv preprint arXiv:2107.04380","author":"Carreira-Perpi\u00f1\u00e1n M.","year":"2021","unstructured":"M. \u00c1. Carreira-Perpi\u00f1\u00e1n and Y. Idelbayev, \"Model compression as constrained optimization, with application to neural nets. part v: combining compressions,\" arXiv preprint arXiv:2107.04380, 2021."},{"key":"e_1_3_2_1_5_1","first-page":"4504","volume-title":"A flexible, extensible open-source toolkit for model compression,\" in Proceedings of the 30th ACM International Conference on Information & Knowledge Management","author":"Idelbayev Y.","year":"2021","unstructured":"Y. Idelbayev and M. \u00c1. Carreira-Perpi\u00f1\u00e1n, \"Lc: A flexible, extensible open-source toolkit for model compression,\" in Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pp. 4504--4514, 2021."},{"key":"e_1_3_2_1_6_1","volume-title":"Exploring the use of synthetic gradients for distributed deep learning across cloud and edge resources,\" in 2nd USENIX Workshop on Hot Topics in Edge Computing (HotEdge 19)","author":"Chen Y.","year":"2019","unstructured":"Y. Chen, K. Zhao, B. Li, and M. Zhao, \"Exploring the use of synthetic gradients for distributed deep learning across cloud and edge resources,\" in 2nd USENIX Workshop on Hot Topics in Edge Computing (HotEdge 19), 2019."},{"key":"e_1_3_2_1_7_1","unstructured":"M. Zhao \"Knowledgenet: Disaggregated and distributed training and serving of deep neural networks \""},{"key":"e_1_3_2_1_8_1","first-page":"127","author":"Chen Y.","year":"2019","unstructured":"Y. Chen, S. Biookaghazadeh, and M. Zhao, \"Exploring the capabilities of mobile devices in supporting deep learning,\" in Proceedings of the 4th ACM\/IEEE Symposium on Edge Computing, pp. 127--138, 2019.","journal-title":"\"Exploring the capabilities of mobile devices in supporting deep learning,\" in Proceedings of the 4th ACM\/IEEE Symposium on Edge Computing"},{"key":"e_1_3_2_1_9_1","volume-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients,\" arXiv preprint arXiv:1606.06160","author":"Zhou S.","year":"2016","unstructured":"S. Zhou, Y. Wu, Z. Ni, X. Zhou, H. Wen, and Y. Zou, \"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients,\" arXiv preprint arXiv:1606.06160, 2016."},{"key":"e_1_3_2_1_10_1","volume-title":"Pact: Parameterized clipping activation for quantized neural networks,\" arXiv preprint arXiv:1805.06085","author":"Choi J.","year":"2018","unstructured":"J. Choi, Z. Wang, S. Venkataramani, P. I.-J. Chuang, V. Srinivasan, and K. Gopalakrishnan, \"Pact: Parameterized clipping activation for quantized neural networks,\" arXiv preprint arXiv:1805.06085, 2018."},{"key":"e_1_3_2_1_11_1","volume-title":"Learned step size quantization,\" arXiv preprint arXiv:1902.08153","author":"Esser S. K.","year":"2019","unstructured":"S. K. Esser, J. L. McKinstry, D. Bablani, R. Appuswamy, and D. S. Modha, \"Learned step size quantization,\" arXiv preprint arXiv:1902.08153, 2019."},{"key":"e_1_3_2_1_12_1","first-page":"6448","author":"Lee J.","year":"2021","unstructured":"J. Lee, D. Kim, and B. Ham, \"Network quantization with element-wise gradient scaling,\" in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 6448--6457, 2021.","journal-title":"\"Network quantization with element-wise gradient scaling,\" in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"e_1_3_2_1_13_1","first-page":"6794","volume":"35","author":"Boo Y.","year":"2021","unstructured":"Y. Boo, S. Shin, J. Choi, and W. Sung, \"Stochastic precision ensemble: self-knowledge distillation for quantized deep neural networks,\" in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 6794--6802, 2021.","journal-title":"\"Stochastic precision ensemble: self-knowledge distillation for quantized deep neural networks,\" in Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_3_2_1_14_1","volume-title":"Mqbench: Towards reproducible and deployable model quantization benchmark,\" arXiv preprint arXiv:2111.03759","author":"Li Y.","year":"2021","unstructured":"Y. Li, M. Shen, J. Ma, Y. Ren, M. Zhao, Q. Zhang, R. Gong, F. Yu, and J. Yan, \"Mqbench: Towards reproducible and deployable model quantization benchmark,\" arXiv preprint arXiv:2111.03759, 2021."},{"key":"e_1_3_2_1_15_1","volume-title":"Estimating or propagating gradients through stochastic neurons for conditional computation,\" arXiv preprint arXiv:1308.3432","author":"Bengio Y.","year":"2013","unstructured":"Y. Bengio, N. L\u00e9onard, and A. Courville, \"Estimating or propagating gradients through stochastic neurons for conditional computation,\" arXiv preprint arXiv:1308.3432, 2013."},{"key":"e_1_3_2_1_16_1","first-page":"41","author":"Bengio Y.","year":"2009","unstructured":"Y. Bengio, J. Louradour, R. Collobert, and J. Weston, \"Curriculum learning,\" in Proceedings of the 26th annual international conference on machine learning, pp. 41--48, 2009.","journal-title":"\"Curriculum learning,\" in Proceedings of the 26th annual international conference on machine learning"},{"key":"e_1_3_2_1_17_1","volume-title":"Distilling the knowledge in a neural network,\" arXiv preprint arXiv:1503.02531","author":"Hinton G.","unstructured":"G. Hinton, O. Vinyals, J. Dean, et al., \"Distilling the knowledge in a neural network,\" arXiv preprint arXiv:1503.02531, vol. 2, no. 7, 2015."},{"key":"e_1_3_2_1_18_1","first-page":"630","volume-title":"Proceedings, Part IV 14","author":"He K.","year":"2016","unstructured":"K. He, X. Zhang, S. Ren, and J. Sun, \"Identity mappings in deep residual networks,\" in Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part IV 14, pp. 630--645, Springer, 2016."},{"key":"e_1_3_2_1_19_1","first-page":"2650","volume-title":"Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture,\" in Proceedings of the IEEE international conference on computer vision","author":"Eigen D.","year":"2015","unstructured":"D. Eigen and R. Fergus, \"Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture,\" in Proceedings of the IEEE international conference on computer vision, pp. 2650--2658, 2015."},{"key":"e_1_3_2_1_20_1","first-page":"4510","volume-title":"Inverted residuals and linear bottlenecks,\" in Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Sandler M.","year":"2018","unstructured":"M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, \"Mobilenetv2: Inverted residuals and linear bottlenecks,\" in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4510--4520, 2018."},{"key":"e_1_3_2_1_21_1","first-page":"6848","volume-title":"Shufflenet: An extremely efficient convolutional neural network for mobile devices,\" in Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Zhang X.","year":"2018","unstructured":"X. Zhang, X. Zhou, M. Lin, and J. Sun, \"Shufflenet: An extremely efficient convolutional neural network for mobile devices,\" in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6848--6856, 2018."},{"key":"e_1_3_2_1_22_1","volume-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size,\" arXiv preprint arXiv:1602.07360","author":"Iandola F. N.","year":"2016","unstructured":"F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, \"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size,\" arXiv preprint arXiv:1602.07360, 2016."},{"key":"e_1_3_2_1_23_1","volume-title":"Imagenet classification with deep convolutional neural networks,\" Advances in neural information processing systems","author":"Krizhevsky A.","year":"2012","unstructured":"A. Krizhevsky, I. Sutskever, and G. E. Hinton, \"Imagenet classification with deep convolutional neural networks,\" Advances in neural information processing systems, vol. 25, 2012."},{"key":"e_1_3_2_1_24_1","volume-title":"Citeseer","author":"Krizhevsky A.","year":"2009","unstructured":"A. Krizhevsky, G. Hinton, et al., \"Learning multiple layers of features from tiny images,\" tech. rep., Citeseer, 2009."},{"key":"e_1_3_2_1_25_1","volume-title":"Tiny imagenet visual recognition challenge,\" CS 231N","author":"Le Y.","unstructured":"Y. Le and X. Yang, \"Tiny imagenet visual recognition challenge,\" CS 231N, vol. 7, no. 7, p. 3, 2015."}],"event":{"name":"SEC '23: Eighth ACM\/IEEE Symposium on Edge Computing","location":"Wilmington DE USA","acronym":"SEC '23","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","IEEE Computer Society"]},"container-title":["Proceedings of the Eighth ACM\/IEEE Symposium on Edge Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583740.3626620","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583740.3626620","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:28Z","timestamp":1750178788000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583740.3626620"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,6]]},"references-count":25,"alternative-id":["10.1145\/3583740.3626620","10.1145\/3583740"],"URL":"https:\/\/doi.org\/10.1145\/3583740.3626620","relation":{},"subject":[],"published":{"date-parts":[[2023,12,6]]},"assertion":[{"value":"2024-08-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}