{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:27:43Z","timestamp":1783528063564,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,14]],"date-time":"2022-08-14T00:00:00Z","timestamp":1660435200000},"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 51NF40_180545"],"award-info":[{"award-number":["NCCR Automation 51NF40_180545"]}]},{"DOI":"10.13039\/501100014790","name":"Singapore Management University","doi-asserted-by":"publisher","award":["Lee Kong Chian Fellowship T050202"],"award-info":[{"award-number":["Lee Kong Chian Fellowship T050202"]}],"id":[{"id":"10.13039\/501100014790","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,14]]},"DOI":"10.1145\/3534678.3539293","type":"proceedings-article","created":{"date-parts":[[2022,8,12]],"date-time":"2022-08-12T19:06:41Z","timestamp":1660331201000},"page":"1441-1451","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["p-Meta"],"prefix":"10.1145","author":[{"given":"Zhongnan","family":"Qu","sequence":"first","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zimu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxin","family":"Tong","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lothar","family":"Thiele","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,8,14]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Antreas Antoniou Harrison Edwards and Amos Storkey. 2019. How to train your MAML. In ICLR ."},{"key":"e_1_3_2_2_2_1","unstructured":"Han Cai Chuang Gan Ligeng Zhu and Song Han. 2020. TinyTL: Reduce Memory Not Parameters for Efficient On-Device Learning. In NeurIPS ."},{"key":"e_1_3_2_2_3_1","volume-title":"Tri Dao, Zhao Song, Anshumali Shrivastava, and Christopher Re.","author":"Chen Beidi","year":"2021","unstructured":"Beidi Chen, Zichang Liu, Binghui Peng, Zhaozhuo Xu, Jonathan Lingjie Li, Tri Dao, Zhao Song, Anshumali Shrivastava, and Christopher Re. 2021. MONGOOSE: A Learnable LSH Framework for Efficient Neural Network Training. In ICLR ."},{"key":"e_1_3_2_2_4_1","unstructured":"Tianqi Chen Bing Xu Chiyuan Zhang and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arxiv: 1604.06174"},{"key":"e_1_3_2_2_5_1","volume-title":"Dynamic Convolution: Attention Over Convolution Kernels. In CVPR .","author":"Chen Yinpeng","year":"2020","unstructured":"Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Lu Yuan, and Zicheng Liu. 2020. Dynamic Convolution: Attention Over Convolution Kernels. In CVPR ."},{"key":"e_1_3_2_2_6_1","unstructured":"Tristan Deleu. 2018. Model-Agnostic Meta-Learning for Reinforcement Learning in PyTorch. Available at: https:\/\/github.com\/tristandeleu\/pytorch-maml-rl."},{"key":"e_1_3_2_2_7_1","volume-title":"Joseph Paul Cohen, and Yoshua Bengio","author":"Deleu Tristan","year":"2019","unstructured":"Tristan Deleu, Tobias W\u00fcrfl, Mandana Samiei, Joseph Paul Cohen, and Yoshua Bengio. 2019. Torchmeta: A Meta-Learning library for PyTorch . https:\/\/arxiv.org\/abs\/1909.06576 Available at: https:\/\/github.com\/tristandeleu\/pytorch-meta."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"e_1_3_2_2_9_1","unstructured":"Yan Duan Xi Chen Rein Houthooft John Schulman and Pieter Abbeel. 2016. Benchmarking Deep Reinforcement Learning for Continuous Control. In ICML ."},{"key":"e_1_3_2_2_10_1","unstructured":"Chelsea Finn Pieter Abbeel and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In ICML ."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Dawei Gao Xiaoxi He Zimu Zhou Yongxin Tong and Lothar Thiele. 2021. Pruning meta-trained networks for on-device adaptation. In CIKM .","DOI":"10.1145\/3459637.3482378"},{"key":"e_1_3_2_2_12_1","unstructured":"Aidan N Gomez Mengye Ren Raquel Urtasun and Roger B Grosse. 2017. The Reversible Residual Network: Backpropagation Without Storing Activations. In NeurIPS ."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Taesik Gong Yeonsu Kim Jinwoo Shin and Sung-Ju Lee. 2019. Metasense: few-shot adaptation to untrained conditions in deep mobile sensing. In SenSys .","DOI":"10.1145\/3356250.3360020"},{"key":"e_1_3_2_2_14_1","volume-title":"Deep learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. 2016. Deep learning. Vol. 1. MIT press Cambridge."},{"key":"e_1_3_2_2_15_1","volume-title":"Petr Zadrazil, Andreas Kabel, Francc oise Beaufays, and Giovanni Motta.","author":"Gooneratne Mary","year":"2020","unstructured":"Mary Gooneratne, Khe Chai Sim, Petr Zadrazil, Andreas Kabel, Francc oise Beaufays, and Giovanni Motta. 2020. Low-rank Gradient Approximation For Memory-Efficient On-device Training of Deep Neural Network. In ICASSP ."},{"key":"e_1_3_2_2_16_1","unstructured":"Priya Goyal Piotr Doll\u00e1r Ross Girshick Pieter Noordhuis Lukasz Wesolowski Aapo Kyrola Andrew Tulloch Yangqing Jia and Kaiming He. 2017. Accurate large minibatch sgd: Training imagenet in 1 hour. arxiv: 1706.02677"},{"key":"e_1_3_2_2_17_1","unstructured":"Klaus Greff Rupesh K. Srivastava and J\u00fcrgen Schmidhuber. 2017. Highway and Residual Networks learn Unrolled Iterative Estimation. In NeurIPS ."},{"key":"e_1_3_2_2_18_1","unstructured":"Audrnas Gruslys Remi Munos Ivo Danihelka Marc Lanctot and Alex Graves. 2016. Memory-Efficient Backpropagation Through Time. In NeurIPS ."},{"key":"e_1_3_2_2_19_1","unstructured":"Liang-Yan Gui Yu-Xiong Wang Deva Ramanan and Jos\u00e9 MF Moura. 2018. Few-shot human motion prediction via meta-learning. In ECCV ."},{"key":"e_1_3_2_2_20_1","unstructured":"Song Han Huizi Mao and William J Dally. 2016. Deep compression: Compressing deep neural networks with pruning trained quantization and huffman coding. In ICLR ."},{"key":"e_1_3_2_2_21_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR ."},{"key":"e_1_3_2_2_22_1","volume-title":"Meta-learning in neural networks: a survey. arxiv","author":"Hospedales Timothy","year":"2004","unstructured":"Timothy Hospedales, Antreas Antoniou, Paul Micaelli, and Amos Storkey. 2020. Meta-learning in neural networks: a survey. arxiv: 2004.05439"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Jie Hu Li Shen and Gang Sun. 2018. Squeeze-and-Excitation Networks. In CVPR .","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_2_24_1","unstructured":"Seulki Lee and Shahriar Nirjon. 2019. Neuro.ZERO: a zero-energy neural network accelerator for embedded sensing and inference systems. In SenSys ."},{"key":"e_1_3_2_2_25_1","volume-title":"Javier Fernandez-Marques, Taner Topal, Xinchi Qiu, Titouan Parcollet, Yan Gao, and Nicholas D. Lane.","author":"Mathur Akhil","year":"2021","unstructured":"Akhil Mathur, Daniel J. Beutel, Pedro Porto Buarque de Gusm\u00e3o, Javier Fernandez-Marques, Taner Topal, Xinchi Qiu, Titouan Parcollet, Yan Gao, and Nicholas D. Lane. 2021. On-device Federated Learning with Flower. In MLSys ."},{"key":"e_1_3_2_2_26_1","volume-title":"BOIL: Towards Representation Change for Few-shot Learning. In ICLR .","author":"Oh Jaehoon","year":"2021","unstructured":"Jaehoon Oh, Hyungjun Yoo, ChangHwan Kim, and Se-Young Yun. 2021. BOIL: Towards Representation Change for Few-shot Learning. In ICLR ."},{"key":"e_1_3_2_2_27_1","volume-title":"TADAM: Task dependent adaptive metric for improved few-shot learning. In NeurIPS .","author":"Oreshkin Boris N.","year":"2018","unstructured":"Boris N. Oreshkin, Pau Rodriguez, and Alexandre Lacoste. 2018. TADAM: Task dependent adaptive metric for improved few-shot learning. In NeurIPS ."},{"key":"e_1_3_2_2_28_1","unstructured":"Aniruddh Raghu Maithra Raghu Samy Bengio and Oriol Vinyals. 2020. Rapid learning or feature reuse? Towards understanding the effectiveness of MAML. In ICLR ."},{"key":"e_1_3_2_2_29_1","volume-title":"Aamodt","author":"Raihan Md Aamir","year":"2020","unstructured":"Md Aamir Raihan and Tor M. Aamodt. 2020. Sparse Weight Activation Training. In NeurIPS ."},{"key":"e_1_3_2_2_30_1","volume-title":"Zemel","author":"Ren Mengye","year":"2018","unstructured":"Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, and Richard S. Zemel. 2018. Meta-Learning for Semi-Supervised Few-Shot Classification. In ICLR ."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_2_32_1","unstructured":"John Schulman Sergey Levine Philipp Moritz Michael I. Jordan and Pieter Abbeel. 2015. Trust Region Policy Optimization. In ICML ."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Zhiqiang Shen Zechun Liu Jie Qin Marios Savvides and Kwang-Ting Cheng. 2021. Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning. In AAAI .","DOI":"10.1609\/aaai.v35i11.17155"},{"key":"e_1_3_2_2_34_1","volume-title":"Zemel","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard S. Zemel. 2017. Prototypical Networks for Few-shot Learning. In NeurIPS ."},{"key":"e_1_3_2_2_35_1","volume-title":"Hospedales","author":"Sung Flood","year":"2018","unstructured":"Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H. S. Torr, and Timothy M. Hospedales. 2018. Learning to Compare: Relation Network for Few-Shot Learning. In CVPR ."},{"key":"e_1_3_2_2_36_1","unstructured":"TensorFlow. [n.d.]. On-Device Training with TensorFlow Lite. https:\/\/www.tensorflow.org\/lite\/examples\/on_device_training\/overview . Accessed: 2022-01--15."},{"key":"e_1_3_2_2_37_1","volume-title":"Mujoco: A physics engine for model-based control. In IROS .","author":"Todorov Emanuel","year":"2012","unstructured":"Emanuel Todorov, Tom Erez, and Yuval Tassa. 2012. Mujoco: A physics engine for model-based control. In IROS ."},{"key":"e_1_3_2_2_38_1","unstructured":"Eleni Triantafillou Tyler Zhu Vincent Dumoulin Pascal Lamblin Utku Evci Kelvin Xu Ross Goroshin Carles Gelada Kevin Swersky Pierre-Antoine Manzagol and Hugo Larochelle. 2020. Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples. In ICLR ."},{"key":"e_1_3_2_2_39_1","unstructured":"Oriol Vinyals Charles Blundell Timothy Lillicrap Koray Kavukcuoglu and Daan Wierstra. 2016. Matching Networks for One Shot Learning. In NeurIPS ."},{"key":"e_1_3_2_2_40_1","unstructured":"Johannes Von Oswald Dominic Zhao Seijin Kobayashi Simon Schug Massimo Caccia Nicolas Zucchet and Jo ao Sacramento. 2021. Learning where to learn: Gradient sparsity in meta and continual learning. In NeurIPS ."},{"key":"e_1_3_2_2_41_1","volume-title":"Technical Report CNS-TR-2010-001. California Institute of Technology.","author":"Welinder P.","year":"2010","unstructured":"P. Welinder, S. Branson, T. Mita, C. Wah, F. Schroff, S. Belongie, and P. Perona. 2010. Caltech-UCSD Birds 200. Technical Report CNS-TR-2010-001. California Institute of Technology."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"e_1_3_2_2_43_1","unstructured":"Yuxin Wu and Kaiming He. 2018. Group Normalization. In ECCV ."}],"event":{"name":"KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Washington DC USA","acronym":"KDD '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539293","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3534678.3539293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:59:59Z","timestamp":1750186799000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3534678.3539293"}},"subtitle":["Towards On-device Deep Model Adaptation"],"short-title":[],"issued":{"date-parts":[[2022,8,14]]},"references-count":43,"alternative-id":["10.1145\/3534678.3539293","10.1145\/3534678"],"URL":"https:\/\/doi.org\/10.1145\/3534678.3539293","relation":{},"subject":[],"published":{"date-parts":[[2022,8,14]]},"assertion":[{"value":"2022-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}