{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:23:52Z","timestamp":1781087032942,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":105,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T00:00:00Z","timestamp":1668384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,14]]},"DOI":"10.1145\/3563766.3564109","type":"proceedings-article","created":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T16:29:31Z","timestamp":1668443371000},"page":"188-197","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Rethinking data-driven networking with foundation models"],"prefix":"10.1145","author":[{"given":"Franck","family":"Le","sequence":"first","affiliation":[{"name":"IBM Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mudhakar","family":"Srivatsa","sequence":"additional","affiliation":[{"name":"IBM Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raghu","family":"Ganti","sequence":"additional","affiliation":[{"name":"IBM Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vyas","family":"Sekar","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,11,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405892"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the KDD Cup Workshop 2007","author":"Bennett J.","year":"2007","unstructured":"J. Bennett and S. Lanning . 2007. The Netflix Prize . In Proceedings of the KDD Cup Workshop 2007 . ACM, New York, 3--6. http:\/\/www.cs.uic.edu\/~liub\/KDD-cup- 2007 \/NetflixPrize-description.pdf J. Bennett and S. Lanning. 2007. The Netflix Prize. In Proceedings of the KDD Cup Workshop 2007. ACM, New York, 3--6. http:\/\/www.cs.uic.edu\/~liub\/KDD-cup-2007\/NetflixPrize-description.pdf"},{"key":"e_1_3_2_1_3_1","unstructured":"Rishi Bommasani Drew A Hudson Ehsan Adeli Russ Altman Simran Arora Sydney von Arx Michael S Bernstein Jeannette Bohg Antoine Bosselut Emma Brunskill etal 2021. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021).  Rishi Bommasani Drew A Hudson Ehsan Adeli Russ Altman Simran Arora Sydney von Arx Michael S Bernstein Jeannette Bohg Antoine Bosselut Emma Brunskill et al. 2021. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6242"},{"key":"e_1_3_2_1_5_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell etal 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901.  Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230551"},{"key":"e_1_3_2_1_8_1","volume-title":"Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems 34","author":"Chen Lili","year":"2021","unstructured":"Lili Chen , Kevin Lu , Aravind Rajeswaran , Kimin Lee , Aditya Grover , Misha Laskin , Pieter Abbeel , Aravind Srinivas , and Igor Mordatch . 2021. Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems 34 ( 2021 ), 15084--15097. Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Misha Laskin, Pieter Abbeel, Aravind Srinivas, and Igor Mordatch. 2021. Decision transformer: Reinforcement learning via sequence modeling. Advances in neural information processing systems 34 (2021), 15084--15097."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research), Hal Daum\u00e9 III and Aarti Singh (Eds.)","volume":"119","author":"Chen Mark","year":"2020","unstructured":"Mark Chen , Alec Radford , Rewon Child , Jeffrey Wu , Heewoo Jun , David Luan , and Ilya Sutskever . 2020 . Generative Pretraining From Pixels . In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research), Hal Daum\u00e9 III and Aarti Singh (Eds.) , Vol. 119 . PMLR, 1691--1703. https:\/\/proceedings.mlr.press\/v119\/chen20s.html Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, and Ilya Sutskever. 2020. Generative Pretraining From Pixels. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research), Hal Daum\u00e9 III and Aarti Singh (Eds.), Vol. 119. PMLR, 1691--1703. https:\/\/proceedings.mlr.press\/v119\/chen20s.html"},{"key":"e_1_3_2_1_10_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen , Jerry Tworek , Heewoo Jun , Qiming Yuan , Henrique Ponde de Oliveira Pinto , Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021 . Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021). Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1009"},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=r1xMH1BtvB","author":"Clark Kevin","unstructured":"Kevin Clark , Minh-Thang Luong , Quoc V. Le , and Christopher D. Manning . 2020. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators . In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=r1xMH1BtvB Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=r1xMH1BtvB"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_1_14_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_15_1","first-page":"05","volume-title":"Proceedings of the Third International Workshop on Paraphrasing (IWP2005)","author":"William","unstructured":"William B. Dolan and Chris Brockett. 2005. Automatically Constructing a Corpus of Sentential Paraphrases . In Proceedings of the Third International Workshop on Paraphrasing (IWP2005) . https:\/\/aclanthology.org\/I 05 - 5002 William B. Dolan and Chris Brockett. 2005. Automatically Constructing a Corpus of Sentential Paraphrases. In Proceedings of the Third International Workshop on Paraphrasing (IWP2005). https:\/\/aclanthology.org\/I05-5002"},{"key":"e_1_3_2_1_16_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly etal 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020).  Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning -","volume":"48","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani . 2016 . Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning . In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 (ICML'16). JMLR.org, 1050--1059. Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 (ICML'16). JMLR.org, 1050--1059."},{"key":"e_1_3_2_1_19_1","volume-title":"Towards automatic concept-based explanations. Advances in Neural Information Processing Systems 32","author":"Ghorbani Amirata","year":"2019","unstructured":"Amirata Ghorbani , James Wexler , James Y Zou , and Been Kim . 2019. Towards automatic concept-based explanations. Advances in Neural Information Processing Systems 32 ( 2019 ). Amirata Ghorbani, James Wexler, James Y Zou, and Been Kim. 2019. Towards automatic concept-based explanations. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1514"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/APCC.2009.5375520"},{"key":"e_1_3_2_1_22_1","volume-title":"Attention is not explanation. arXiv preprint arXiv:1902.10186","author":"Jain Sarthak","year":"2019","unstructured":"Sarthak Jain and Byron C Wallace . 2019. Attention is not explanation. arXiv preprint arXiv:1902.10186 ( 2019 ). Sarthak Jain and Byron C Wallace. 2019. Attention is not explanation. arXiv preprint arXiv:1902.10186 (2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"Offline reinforcement learning as one big sequence modeling problem. Advances in neural information processing systems 34","author":"Janner Michael","year":"2021","unstructured":"Michael Janner , Qiyang Li , and Sergey Levine . 2021. Offline reinforcement learning as one big sequence modeling problem. Advances in neural information processing systems 34 ( 2021 ), 1273--1286. Michael Janner, Qiyang Li, and Sergey Levine. 2021. Offline reinforcement learning as one big sequence modeling problem. Advances in neural information processing systems 34 (2021), 1273--1286."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.)","volume":"97","author":"Jay Nathan","year":"2019","unstructured":"Nathan Jay , Noga Rotman , Brighten Godfrey , Michael Schapira , and Aviv Tamar . 2019 . A Deep Reinforcement Learning Perspective on Internet Congestion Control . In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.) , Vol. 97 . PMLR, 3050--3059. https:\/\/proceedings.mlr.press\/v97\/jay19a.html Nathan Jay, Noga Rotman, Brighten Godfrey, Michael Schapira, and Aviv Tamar. 2019. A Deep Reinforcement Learning Perspective on Internet Congestion Control. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.), Vol. 97. PMLR, 3050--3059. https:\/\/proceedings.mlr.press\/v97\/jay19a.html"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"e_1_3_2_1_26_1","volume-title":"Neural machine translation in linear time. arXiv preprint arXiv:1610.10099","author":"Kalchbrenner Nal","year":"2016","unstructured":"Nal Kalchbrenner , Lasse Espeholt , Karen Simonyan , Aaron van den Oord , Alex Graves , and Koray Kavukcuoglu . 2016. Neural machine translation in linear time. arXiv preprint arXiv:1610.10099 ( 2016 ). Nal Kalchbrenner, Lasse Espeholt, Karen Simonyan, Aaron van den Oord, Alex Graves, and Koray Kavukcuoglu. 2016. Neural machine translation in linear time. arXiv preprint arXiv:1610.10099 (2016)."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research), Hal Daum\u00e9 III and Aarti Singh (Eds.)","volume":"119","author":"Kanade Aditya","year":"2020","unstructured":"Aditya Kanade , Petros Maniatis , Gogul Balakrishnan , and Kensen Shi . 2020 . Learning and Evaluating Contextual Embedding of Source Code . In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research), Hal Daum\u00e9 III and Aarti Singh (Eds.) , Vol. 119 . PMLR, 5110--5121. https:\/\/proceedings.mlr.press\/v119\/kanade20a.html Aditya Kanade, Petros Maniatis, Gogul Balakrishnan, and Kensen Shi. 2020. Learning and Evaluating Contextual Embedding of Source Code. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research), Hal Daum\u00e9 III and Aarti Singh (Eds.), Vol. 119. PMLR, 5110--5121. https:\/\/proceedings.mlr.press\/v119\/kanade20a.html"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1644893.1644918"},{"key":"e_1_3_2_1_29_1","volume-title":"Survey-lance: Automatically Detecting Online Survey Scams. In 2018 IEEE Symposium on Security and Privacy (SP). IEEE, 70--86","author":"Kharraz Amin","year":"2018","unstructured":"Amin Kharraz ,, William Robertson , and Engin Kirda . 2018 . Survey-lance: Automatically Detecting Online Survey Scams. In 2018 IEEE Symposium on Security and Privacy (SP). IEEE, 70--86 . Amin Kharraz,, William Robertson, and Engin Kirda. 2018. Survey-lance: Automatically Detecting Online Survey Scams. In 2018 IEEE Symposium on Security and Privacy (SP). IEEE, 70--86."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/1251086.1251109"},{"key":"e_1_3_2_1_31_1","volume-title":"Learning to optimize join queries with deep reinforcement learning. arXiv preprint arXiv:1808.03196","author":"Krishnan Sanjay","year":"2018","unstructured":"Sanjay Krishnan , Zongheng Yang , Ken Goldberg , Joseph Hellerstein , and Ion Stoica . 2018. Learning to optimize join queries with deep reinforcement learning. arXiv preprint arXiv:1808.03196 ( 2018 ). Sanjay Krishnan, Zongheng Yang, Ken Goldberg, Joseph Hellerstein, and Ion Stoica. 2018. Learning to optimize join queries with deep reinforcement learning. arXiv preprint arXiv:1808.03196 (2018)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295387"},{"key":"e_1_3_2_1_33_1","volume-title":"Unmasking Clever Hans predictors and assessing what machines really learn. Nature communications 10, 1","author":"Lapuschkin Sebastian","year":"2019","unstructured":"Sebastian Lapuschkin , Stephan W\u00e4ldchen , Alexander Binder , Gr\u00e9goire Montavon , Wojciech Samek , and Klaus-Robert M\u00fcller . 2019. Unmasking Clever Hans predictors and assessing what machines really learn. Nature communications 10, 1 ( 2019 ), 1--8. Sebastian Lapuschkin, Stephan W\u00e4ldchen, Alexander Binder, Gr\u00e9goire Montavon, Wojciech Samek, and Klaus-Robert M\u00fcller. 2019. Unmasking Clever Hans predictors and assessing what machines really learn. Nature communications 10, 1 (2019), 1--8."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2206.10472"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00067"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327757.3327819"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3031843.3031909"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2068816.2068837"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342221"},{"key":"e_1_3_2_1_40_1","volume-title":"Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690","author":"Liang Shiyu","year":"2017","unstructured":"Shiyu Liang , Yixuan Li , and Rayadurgam Srikant . 2017. Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690 ( 2017 ). Shiyu Liang, Yixuan Li, and Rayadurgam Srikant. 2017. Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690 (2017)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2003.1167344"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00141"},{"key":"e_1_3_2_1_43_1","first-page":"7498","article-title":"Simple and principled uncertainty estimation with deterministic deep learning via distance awareness","volume":"33","author":"Liu Jeremiah","year":"2020","unstructured":"Jeremiah Liu , Zi Lin , Shreyas Padhy , Dustin Tran , Tania Bedrax Weiss , and Balaji Lakshminarayanan . 2020 . Simple and principled uncertainty estimation with deterministic deep learning via distance awareness . Advances in Neural Information Processing Systems 33 (2020), 7498 -- 7512 . Jeremiah Liu, Zi Lin, Shreyas Padhy, Dustin Tran, Tania Bedrax Weiss, and Balaji Lakshminarayanan. 2020. Simple and principled uncertainty estimation with deterministic deep learning via distance awareness. Advances in Neural Information Processing Systems 33 (2020), 7498--7512.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671639"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497526"},{"key":"e_1_3_2_1_46_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu , Myle Ott , Naman Goyal , Jingfei Du , Mandar Joshi , Danqi Chen , Omer Levy , Mike Lewis , Luke Zettlemoyer , and Veselin Stoyanov . 2019 . Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019). Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_47_1","volume-title":"NetBERT: A Pre-trained Language Representation Model for Computer Networking. Master's thesis","author":"Louis Antoine","unstructured":"Antoine Louis . 2020. NetBERT: A Pre-trained Language Representation Model for Computer Networking. Master's thesis . University of Li\u00e8ge , Li\u00e8ge, Belgium. http:\/\/hdl.handle.net\/2268.2\/9060 Antoine Louis. 2020. NetBERT: A Pre-trained Language Representation Model for Computer Networking. Master's thesis. University of Li\u00e8ge, Li\u00e8ge, Belgium. http:\/\/hdl.handle.net\/2268.2\/9060"},{"key":"e_1_3_2_1_48_1","volume-title":"A unified approach to interpreting model predictions. Advances in neural information processing systems 30","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee . 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 ( 2017 ). Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405868"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405859"},{"key":"e_1_3_2_1_53_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov , Kai Chen , Greg Corrado , and Jeffrey Dean . 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 ( 2013 ). Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov , Wen-tau Yih, and Geoffrey Zweig . 2013 . Linguistic Regularities in Continuous Space Word Representations . In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics , Atlanta, Georgia, 746--751. https:\/\/aclanthology.org\/N13-1090 Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. 2013. Linguistic Regularities in Continuous Space Word Representations. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Atlanta, Georgia, 746--751. https:\/\/aclanthology.org\/N13-1090"},{"key":"e_1_3_2_1_55_1","first-page":"1532","article-title":"Glove: Global Vectors for Word Representation","volume":"14","author":"Pennington Jeffrey","year":"2014","unstructured":"Jeffrey Pennington , Richard Socher , and Christopher D Manning . 2014 . Glove: Global Vectors for Word Representation .. In EMNLP , Vol. 14. 1532 -- 1543 . Jeffrey Pennington, Richard Socher, and Christopher D Manning. 2014. Glove: Global Vectors for Word Representation.. In EMNLP, Vol. 14. 1532--1543.","journal-title":"EMNLP"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP52444.2021.9651937"},{"key":"e_1_3_2_1_57_1","volume-title":"CoNLL-2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes. In Joint Conference on EMNLP and CoNLL - Shared Task. Association for Computational Linguistics","author":"Pradhan Sameer","year":"2012","unstructured":"Sameer Pradhan , Alessandro Moschitti , Nianwen Xue , Olga Uryupina , and Yuchen Zhang . 2012 . CoNLL-2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes. In Joint Conference on EMNLP and CoNLL - Shared Task. Association for Computational Linguistics , Jeju Island, Korea, 1--40. https:\/\/aclanthology.org\/W12-4501 Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes. In Joint Conference on EMNLP and CoNLL - Shared Task. Association for Computational Linguistics, Jeju Island, Korea, 1--40. https:\/\/aclanthology.org\/W12-4501"},{"key":"e_1_3_2_1_58_1","volume-title":"Learning to generate reviews and discovering sentiment. arXiv preprint arXiv:1704.01444","author":"Radford Alec","year":"2017","unstructured":"Alec Radford , Rafal Jozefowicz , and Ilya Sutskever . 2017. Learning to generate reviews and discovering sentiment. arXiv preprint arXiv:1704.01444 ( 2017 ). Alec Radford, Rafal Jozefowicz, and Ilya Sutskever. 2017. Learning to generate reviews and discovering sentiment. arXiv preprint arXiv:1704.01444 (2017)."},{"key":"e_1_3_2_1_59_1","volume-title":"International Conference on Machine Learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford , Jong Wook Kim , Chris Hallacy , Aditya Ramesh , Gabriel Goh , Sandhini Agarwal , Girish Sastry , Amanda Askell , Pamela Mishkin , Jack Clark , 2021 . Learning transferable visual models from natural language supervision . In International Conference on Machine Learning. PMLR, 8748--8763 . Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_60_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel , Noam Shazeer , Adam Roberts , Katherine Lee , Sharan Narang , Michael Matena , Yanqi Zhou , Wei Li , Peter J Liu , 2020 . Exploring the limits of transfer learning with a unified text-to-text transformer . J. Mach. Learn. Res. 21 , 140 (2020), 1 -- 67 . Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J Liu, et al. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140 (2020), 1--67.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_62_1","volume-title":"Garnett (Eds.)","volume":"32","author":"Reif Emily","year":"2019","unstructured":"Emily Reif , Ann Yuan , Martin Wattenberg , Fernanda B Viegas , Andy Coenen , Adam Pearce , and Been Kim . 2019 . Visualizing and Measuring the Geometry of BERT. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R . Garnett (Eds.) , Vol. 32 . Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/ 2019\/file\/159c1ffe5b61b41b3c4d8f4c2150f6c4-Paper.pdf Emily Reif, Ann Yuan, Martin Wattenberg, Fernanda B Viegas, Andy Coenen, Adam Pearce, and Been Kim. 2019. Visualizing and Measuring the Geometry of BERT. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alch\u00e9-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/159c1ffe5b61b41b3c4d8f4c2150f6c4-Paper.pdf"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71617-4_6"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314148.3314357"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314148.3314357"},{"key":"e_1_3_2_1_67_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh , Lysandre Debut , Julien Chaumond , and Thomas Wolf . 2019. DistilBERT , a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 ( 2019 ). Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_2_1_70_1","volume-title":"Is attention interpretable? arXiv preprint arXiv:1906.03731","author":"Serrano Sofia","year":"2019","unstructured":"Sofia Serrano and Noah A Smith . 2019. Is attention interpretable? arXiv preprint arXiv:1906.03731 ( 2019 ). Sofia Serrano and Noah A Smith. 2019. Is attention interpretable? arXiv preprint arXiv:1906.03731 (2019)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-6106"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2866249"},{"key":"e_1_3_2_1_73_1","volume-title":"Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825","author":"Smilkov Daniel","year":"2017","unstructured":"Daniel Smilkov , Nikhil Thorat , Been Kim , Fernanda Vi\u00e9gas , and Martin Wattenberg . 2017. Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 ( 2017 ). Daniel Smilkov, Nikhil Thorat, Been Kim, Fernanda Vi\u00e9gas, and Martin Wattenberg. 2017. Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.5555\/1304596.1304846"},{"key":"e_1_3_2_1_75_1","volume-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics","author":"Socher Richard","year":"2013","unstructured":"Richard Socher , Alex Perelygin , Jean Wu , Jason Chuang , Christopher D. Manning , Andrew Ng , and Christopher Potts . 2013 . Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank . In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics , Seattle, Washington, USA, 1631--1642. https:\/\/aclanthology.org\/D13-1170 Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. 2013. Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Seattle, Washington, USA, 1631--1642. https:\/\/aclanthology.org\/D13-1170"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2010.25"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/1005686.1005733"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.03.007"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"e_1_3_2_1_80_1","volume-title":"International conference on machine learning. PMLR, 3319--3328","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan , Ankur Taly , and Qiqi Yan . 2017 . Axiomatic attribution for deep networks . In International conference on machine learning. PMLR, 3319--3328 . Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International conference on machine learning. PMLR, 3319--3328."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.26"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/1151659.1159928"},{"key":"e_1_3_2_1_83_1","volume-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461","author":"Wang Alex","year":"2018","unstructured":"Alex Wang , Amanpreet Singh , Julian Michael , Felix Hill , Omer Levy , and Samuel R Bowman . 2018 . GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018). Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)."},{"key":"e_1_3_2_1_84_1","volume-title":"Structbert: Incorporating language structures into pre-training for deep language understanding. arXiv preprint arXiv:1908.04577","author":"Wang Wei","year":"2019","unstructured":"Wei Wang , Bin Bi , Ming Yan , Chen Wu , Zuyi Bao , Jiangnan Xia , Liwei Peng , and Luo Si . 2019 . Structbert: Incorporating language structures into pre-training for deep language understanding. arXiv preprint arXiv:1908.04577 (2019). Wei Wang, Bin Bi, Ming Yan, Chen Wu, Zuyi Bao, Jiangnan Xia, Liwei Peng, and Luo Si. 2019. Structbert: Incorporating language structures into pre-training for deep language understanding. arXiv preprint arXiv:1908.04577 (2019)."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487552.3487860"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/1140086.1140094"},{"key":"e_1_3_2_1_88_1","volume-title":"Attention is not not explanation. arXiv preprint arXiv:1908.04626","author":"Wiegreffe Sarah","year":"2019","unstructured":"Sarah Wiegreffe and Yuval Pinter . 2019. Attention is not not explanation. arXiv preprint arXiv:1908.04626 ( 2019 ). Sarah Wiegreffe and Yuval Pinter. 2019. Attention is not not explanation. arXiv preprint arXiv:1908.04626 (2019)."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486020"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326285.3329056"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87839-9_1"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00034"},{"key":"e_1_3_2_1_94_1","volume-title":"Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems 32","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang , Zihang Dai , Yiming Yang , Jaime Carbonell , Russ R Salakhutdinov , and Quoc V Le . 2019 . Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems 32 (2019). Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472910"},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291216"},{"key":"e_1_3_2_1_97_1","volume-title":"TaBERT: Pretraining for joint understanding of textual and tabular data. arXiv preprint arXiv:2005.08314","author":"Yin Pengcheng","year":"2020","unstructured":"Pengcheng Yin , Graham Neubig , Wen-tau Yih, and Sebastian Riedel . 2020. TaBERT: Pretraining for joint understanding of textual and tabular data. arXiv preprint arXiv:2005.08314 ( 2020 ). Pengcheng Yin, Graham Neubig, Wen-tau Yih, and Sebastian Riedel. 2020. TaBERT: Pretraining for joint understanding of textual and tabular data. arXiv preprint arXiv:2005.08314 (2020)."},{"key":"e_1_3_2_1_98_1","volume-title":"Swag: A large-scale adversarial dataset for grounded commonsense inference. arXiv preprint arXiv:1808.05326","author":"Zellers Rowan","year":"2018","unstructured":"Rowan Zellers , Yonatan Bisk , Roy Schwartz , and Yejin Choi . 2018 . Swag: A large-scale adversarial dataset for grounded commonsense inference. arXiv preprint arXiv:1808.05326 (2018). Rowan Zellers, Yonatan Bisk, Roy Schwartz, and Yejin Choi. 2018. Swag: A large-scale adversarial dataset for grounded commonsense inference. arXiv preprint arXiv:1808.05326 (2018)."},{"key":"e_1_3_2_1_99_1","volume-title":"When NFV Meets ANN: Rethinking Elastic Scaling for ANN-based NFs","author":"Zhang Menghao","year":"2019","unstructured":"Menghao Zhang , Jiasong Bai , Guanyu Li , Zili Meng , Hongda Li , Hongxin Hu , and Mingwei Xu. 2019. When NFV Meets ANN: Rethinking Elastic Scaling for ANN-based NFs .. In ICNP. IEEE , 1--6. http:\/\/dblp.uni-trier.de\/db\/conf\/icnp\/icnp 2019 .html#ZhangBLMLHX19 Menghao Zhang, Jiasong Bai, Guanyu Li, Zili Meng, Hongda Li, Hongxin Hu, and Mingwei Xu. 2019. When NFV Meets ANN: Rethinking Elastic Scaling for ANN-based NFs.. In ICNP. IEEE, 1--6. http:\/\/dblp.uni-trier.de\/db\/conf\/icnp\/icnp2019.html#ZhangBLMLHX19"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472926"},{"key":"e_1_3_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1004"},{"key":"e_1_3_2_1_102_1","volume-title":"ERNIE: Enhanced language representation with informative entities. arXiv preprint arXiv:1905.07129","author":"Zhang Zhengyan","year":"2019","unstructured":"Zhengyan Zhang , Xu Han , Zhiyuan Liu , Xin Jiang , Maosong Sun , and Qun Liu . 2019 . ERNIE: Enhanced language representation with informative entities. arXiv preprint arXiv:1905.07129 (2019). Zhengyan Zhang, Xu Han, Zhiyuan Liu, Xin Jiang, Maosong Sun, and Qun Liu. 2019. ERNIE: Enhanced language representation with informative entities. arXiv preprint arXiv:1905.07129 (2019)."},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1145\/3232565.3232569"},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472902"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"}],"event":{"name":"HotNets '22: The 21st ACM Workshop on Hot Topics in Networks","location":"Austin Texas","acronym":"HotNets '22","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the 21st ACM Workshop on Hot Topics in Networks"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563766.3564109","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3563766.3564109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:07Z","timestamp":1750186807000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3563766.3564109"}},"subtitle":["challenges and opportunities"],"short-title":[],"issued":{"date-parts":[[2022,11,14]]},"references-count":105,"alternative-id":["10.1145\/3563766.3564109","10.1145\/3563766"],"URL":"https:\/\/doi.org\/10.1145\/3563766.3564109","relation":{},"subject":[],"published":{"date-parts":[[2022,11,14]]},"assertion":[{"value":"2022-11-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}