{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:17:54Z","timestamp":1760710674375,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,14]],"date-time":"2021-08-14T00:00:00Z","timestamp":1628899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Swiss National Science Foundation","award":["NCCR Automation"],"award-info":[{"award-number":["NCCR Automation"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0101100"],"award-info":[{"award-number":["2018AAA0101100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation of China","award":["61822201 and 62076017"],"award-info":[{"award-number":["61822201 and 62076017"]}]},{"name":"Singapore Ministry of Education (MOE) Academic Research Fund (AcRF) Tier 1","award":["19-C220-SMU-012"],"award-info":[{"award-number":["19-C220-SMU-012"]}]},{"name":"CAAI Huawei MindSpore Open Fund","award":["CAAIXSJLJJ-2020-020-A"],"award-info":[{"award-number":["CAAIXSJLJJ-2020-020-A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,14]]},"DOI":"10.1145\/3447548.3467271","type":"proceedings-article","created":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T06:13:10Z","timestamp":1628748790000},"page":"585-595","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Pruning-Aware Merging for Efficient Multitask Inference"],"prefix":"10.1145","author":[{"given":"Xiaoxi","family":"He","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"given":"Dawei","family":"Gao","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}]},{"given":"Zimu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}]},{"given":"Yongxin","family":"Tong","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}]},{"given":"Lothar","family":"Thiele","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2021,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"International Workshop on Independent Component Analysis and Blind Signal Separation: ICA. IEEE Press","author":"Bell Anthony J","year":"2003","unstructured":"Anthony J Bell . 2003 . The co-information lattice . In International Workshop on Independent Component Analysis and Blind Signal Separation: ICA. IEEE Press , Piscataway, NJ, USA, 921--926. Anthony J Bell. 2003. The co-information lattice. In International Workshop on Independent Component Analysis and Blind Signal Separation: ICA. IEEE Press, Piscataway, NJ, USA, 921--926."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/283"},{"volume-title":"ICML","author":"Dai Bin","key":"e_1_3_2_2_3_1","unstructured":"Bin Dai , Chen Zhu , Baining Guo , and David Wipf . 2018. Compressing neural networks using the variational information bottleneck . In ICML . ACM , New York, NY, USA , 1143--1152. Bin Dai, Chen Zhu, Baining Guo, and David Wipf. 2018. Compressing neural networks using the variational information bottleneck. In ICML. ACM, New York, NY, USA, 1143--1152."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"e_1_3_2_2_5_1","volume-title":"Nando De Freitas, et almbox","author":"Denil Misha","year":"2013","unstructured":"Misha Denil , Babak Shakibi , Laurent Dinh , Nando De Freitas, et almbox . 2013 . Predicting parameters in deep learning. In NeurIPS. Curran Associates Inc., Red Hook, NY, USA , 2148--2156. Misha Denil, Babak Shakibi, Laurent Dinh, Nando De Freitas, et almbox. 2013. Predicting parameters in deep learning. In NeurIPS. Curran Associates Inc., Red Hook, NY, USA, 2148--2156."},{"volume-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon","author":"Dong Xin","key":"e_1_3_2_2_6_1","unstructured":"Xin Dong , Shangyu Chen , and Sinno Pan . 2017. Learning to prune deep neural networks via layer-wise optimal brain surgeon . In NeurIPS. Curran Associates Inc., Red Hook, NY, USA , 4860--4874. Xin Dong, Shangyu Chen, and Sinno Pan. 2017. Learning to prune deep neural networks via layer-wise optimal brain surgeon. In NeurIPS. Curran Associates Inc., Red Hook, NY, USA, 4860--4874."},{"volume-title":"MobiCom","author":"Fang Biyi","key":"e_1_3_2_2_7_1","unstructured":"Biyi Fang , Xiao Zeng , and Mi Zhang . 2018. NestDNN: resource-aware multi-tenant on-device deep learning for continuous mobile vision . In MobiCom . ACM , New York, NY, USA , 115--127. Biyi Fang, Xiao Zeng, and Mi Zhang. 2018. NestDNN: resource-aware multi-tenant on-device deep learning for continuous mobile vision. In MobiCom. ACM, New York, NY, USA, 115--127."},{"volume-title":"KDD","author":"Gao Dawei","key":"e_1_3_2_2_8_1","unstructured":"Dawei Gao , Xiaoxi He , Zimu Zhou , Yongxin Tong , Ke Xu , and Lothar Thiele . 2020. Rethinking Pruning for Accelerating Deep Inference At the Edge . In KDD . ACM , New York, NY, USA , 155--164. Dawei Gao, Xiaoxi He, Zimu Zhou, Yongxin Tong, Ke Xu, and Lothar Thiele. 2020. Rethinking Pruning for Accelerating Deep Inference At the Edge. In KDD. ACM, New York, NY, USA, 155--164."},{"volume-title":"Dynamic network surgery for efficient dnns","author":"Guo Yiwen","key":"e_1_3_2_2_9_1","unstructured":"Yiwen Guo , Anbang Yao , and Yurong Chen . 2016. Dynamic network surgery for efficient dnns . In NeurIPS. Curran Associates Inc., Red Hook, NY, USA , 1379--1387. Yiwen Guo, Anbang Yao, and Yurong Chen. 2016. Dynamic network surgery for efficient dnns. In NeurIPS. Curran Associates Inc., Red Hook, NY, USA, 1379--1387."},{"volume-title":"ISCA","author":"Han Song","key":"e_1_3_2_2_10_1","unstructured":"Song Han , Xingyu Liu , Huizi Mao , Jing Pu , Ardavan Pedram , Mark A Horowitz , and William J Dally . 2016. EIE: efficient inference engine on compressed deep neural network . In ISCA . ACM , New York, NY, USA , 243--254. Song Han, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark A Horowitz, and William J Dally. 2016. EIE: efficient inference engine on compressed deep neural network. In ISCA. ACM, New York, NY, USA, 243--254."},{"volume-title":"Deep Residual Learning for Image Recognition","author":"He Kaiming","key":"e_1_3_2_2_11_1","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2016. Deep Residual Learning for Image Recognition . In CVPR. IEEE Press , Piscataway, NJ, USA , 770--778. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR. IEEE Press, Piscataway, NJ, USA, 770--778."},{"key":"e_1_3_2_2_12_1","volume-title":"Pruning-aware xxx merging for efficient multitask inference. arxiv","author":"He Xiaoxi","year":"1905","unstructured":"Xiaoxi He , Dawei Gao , Zimu Zhou , Yongxin Tong , and Lothar Thiele . 2019. Pruning-aware xxx merging for efficient multitask inference. arxiv : 1905 .09676 Xiaoxi He, Dawei Gao, Zimu Zhou, Yongxin Tong, and Lothar Thiele. 2019. Pruning-aware xxx merging for efficient multitask inference. arxiv: 1905.09676"},{"volume-title":"Multi-task zipping via layer-wise neuron sharing","author":"He Xiaoxi","key":"e_1_3_2_2_13_1","unstructured":"Xiaoxi He , Zimu Zhou , and Lothar Thiele . 2018. Multi-task zipping via layer-wise neuron sharing . In NeurIPS. Curran Associates Inc., Red Hook, NY, USA , 6016--6026. Xiaoxi He, Zimu Zhou, and Lothar Thiele. 2018. Multi-task zipping via layer-wise neuron sharing. In NeurIPS. Curran Associates Inc., Red Hook, NY, USA, 6016--6026."},{"volume-title":"Learning to align from scratch","author":"Huang Gary","key":"e_1_3_2_2_14_1","unstructured":"Gary Huang , Marwan Mattar , Honglak Lee , and Erik G Learned-Miller . 2012. Learning to align from scratch . In NeurIPS. Curran Associates Inc., Red Hook, NY, USA , 764--772. Gary Huang, Marwan Mattar, Honglak Lee, and Erik G Learned-Miller. 2012. Learning to align from scratch. In NeurIPS. Curran Associates Inc., Red Hook, NY, USA, 764--772."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.3390\/e19070361"},{"volume-title":"Attribute and simile classifiers for face verification","author":"Kumar Neeraj","key":"e_1_3_2_2_16_1","unstructured":"Neeraj Kumar , Alexander C Berg , Peter N Belhumeur , and Shree K Nayar . 2009. Attribute and simile classifiers for face verification . In ICCV. IEEE Press , Piscataway, NJ, USA , 365--372. Neeraj Kumar, Alexander C Berg, Peter N Belhumeur, and Shree K Nayar. 2009. Attribute and simile classifiers for face verification. In ICCV. IEEE Press, Piscataway, NJ, USA, 365--372."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"volume-title":"MobiSys","author":"Lee Seulki","key":"e_1_3_2_2_18_1","unstructured":"Seulki Lee and Shahriar Nirjon . 2020. Fast and scalable in-memory deep multitask learning via neural weight virtualization . In MobiSys . ACM , New York, NY, USA , 175--190. Seulki Lee and Shahriar Nirjon. 2020. Fast and scalable in-memory deep multitask learning via neural weight virtualization. In MobiSys. ACM, New York, NY, USA, 175--190."},{"key":"e_1_3_2_2_19_1","unstructured":"Hao Li Asim Kadav Igor Durdanovic Hanan Samet and Hans Peter Graf. 2017. Pruning filters for efficient convnets. In ICLR.  Hao Li Asim Kadav Igor Durdanovic Hanan Samet and Hans Peter Graf. 2017. Pruning filters for efficient convnets. In ICLR."},{"volume-title":"Deep learning face attributes in the wild","author":"Liu Ziwei","key":"e_1_3_2_2_20_1","unstructured":"Ziwei Liu , Ping Luo , Xiaogang Wang , and Xiaoou Tang . 2015. Deep learning face attributes in the wild . In ICCV. IEEE Press , Piscataway, NJ, USA , 3730--3738. Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. 2015. Deep learning face attributes in the wild. In ICCV. IEEE Press, Piscataway, NJ, USA, 3730--3738."},{"volume-title":"Importance estimation for neural network pruning","author":"Molchanov Pavlo","key":"e_1_3_2_2_21_1","unstructured":"Pavlo Molchanov , Arun Mallya , Stephen Tyree , Iuri Frosio , and Jan Kautz . 2019. Importance estimation for neural network pruning . In CVPR. IEEE Press , Piscataway, NJ, USA , 11264--11272. Pavlo Molchanov, Arun Mallya, Stephen Tyree, Iuri Frosio, and Jan Kautz. 2019. Importance estimation for neural network pruning. In CVPR. IEEE Press, Piscataway, NJ, USA, 11264--11272."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0940-3"},{"key":"e_1_3_2_2_23_1","volume-title":"Brendan Daniel Tracey, and David Daniel Cox","author":"Saxe Andrew Michael","year":"2018","unstructured":"Andrew Michael Saxe , Yamini Bansal , Joel Dapello , Madhu Advani , Artemy Kolchinsky , Brendan Daniel Tracey, and David Daniel Cox . 2018 . On the information bottleneck theory of deep learning. In ICLR. Andrew Michael Saxe, Yamini Bansal, Joel Dapello, Madhu Advani, Artemy Kolchinsky, Brendan Daniel Tracey, and David Daniel Cox. 2018. On the information bottleneck theory of deep learning. In ICLR."},{"key":"e_1_3_2_2_24_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arxiv: 1409.1556  Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arxiv: 1409.1556"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"e_1_3_2_2_27_1","volume-title":"NeurIPS. Curran Associates Inc.","author":"Wen Wei","year":"2016","unstructured":"Wei Wen , Chunpeng Wu , Yandan Wang , Yiran Chen , and Hai Li . 2016 . Learning structured sparsity in deep neural networks . In NeurIPS. Curran Associates Inc. , Red Hook, NY, USA , 2074--2082. Wei Wen, Chunpeng Wu, Yandan Wang, Yiran Chen, and Hai Li. 2016. Learning structured sparsity in deep neural networks. In NeurIPS. Curran Associates Inc., Red Hook, NY, USA, 2074--2082."},{"key":"e_1_3_2_2_28_1","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arxiv: 1708.07747  Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arxiv: 1708.07747"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx105"}],"event":{"name":"KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Virtual Event Singapore","acronym":"KDD '21"},"container-title":["Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467271","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3447548.3467271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:28Z","timestamp":1750191508000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447548.3467271"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,14]]},"references-count":29,"alternative-id":["10.1145\/3447548.3467271","10.1145\/3447548"],"URL":"https:\/\/doi.org\/10.1145\/3447548.3467271","relation":{},"subject":[],"published":{"date-parts":[[2021,8,14]]},"assertion":[{"value":"2021-08-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}