{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:01:35Z","timestamp":1760598095390,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,26]],"date-time":"2021-10-26T00:00:00Z","timestamp":1635206400000},"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":[[2021,10,26]]},"DOI":"10.1145\/3459637.3481911","type":"proceedings-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T15:53:43Z","timestamp":1636991623000},"page":"4075-4084","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["EasyTransfer"],"prefix":"10.1145","author":[{"given":"Minghui","family":"Qiu","sequence":"first","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haojie","family":"Pan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ang","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cen","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianyan","family":"Jia","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaliang","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deng","family":"Cai","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Lin","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Longformer: The Long-Document Transformer. arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy , Matthew E. Peters , and Arman Cohan . 2020 . Longformer: The Long-Document Transformer. arXiv:2004.05150 (2020). Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2020. Longformer: The Long-Document Transformer. arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_1_2_1","unstructured":"John Blitzer Mark Dredze and Fernando Pereira. 2007. Biographies Bollywood Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification. In ACL. John Blitzer Mark Dredze and Fernando Pereira. 2007. Biographies Bollywood Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification. In ACL."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"D. Chen Y. Li M. Qiu Z. Wang B. Li B. Ding H. Deng J. Huang W. Lin and J. Zhou. 2020. AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search. In IJCAI. 2463--2469. D. Chen Y. Li M. Qiu Z. Wang B. Li B. Ding H. Deng J. Huang W. Lin and J. Zhou. 2020. AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search. In IJCAI. 2463--2469.","DOI":"10.24963\/ijcai.2020\/341"},{"key":"e_1_3_2_1_4_1","unstructured":"Minmin Chen Kilian Q Weinberger and John Blitzer. 2011. Co-training for domain adaptation. In NeurIPS. 2456--2464. Minmin Chen Kilian Q Weinberger and John Blitzer. 2011. Co-training for domain adaptation. In NeurIPS. 2456--2464."},{"key":"e_1_3_2_1_5_1","volume-title":"Generating Long Sequences with Sparse Transformers. arXiv:1904.10509","author":"Child Rewon","year":"2019","unstructured":"Rewon Child , Scott Gray , Alec Radford , and Ilya Sutskever . 2019. Generating Long Sequences with Sparse Transformers. arXiv:1904.10509 ( 2019 ). Rewon Child, Scott Gray, Alec Radford, and Ilya Sutskever. 2019. Generating Long Sequences with Sparse Transformers. arXiv:1904.10509 (2019)."},{"key":"e_1_3_2_1_6_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2019 . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT."},{"key":"e_1_3_2_1_7_1","unstructured":"Dehong Gao Linbo Jin Ben Chen Minghui Qiu Peng Li Yi Wei Yi Hu and Hao Wang. 2020. FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval. In SIGIR. Dehong Gao Linbo Jin Ben Chen Minghui Qiu Peng Li Yi Wei Yi Hu and Hao Wang. 2020. FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval. In SIGIR."},{"key":"e_1_3_2_1_8_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR. 770--778. Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR. 770--778."},{"key":"e_1_3_2_1_9_1","volume-title":"NIPS Deep Learning and Representation Learning Workshop.","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton , Oriol Vinyals , and Jeffrey Dean . 2015 . Distilling the Knowledge in a Neural Network . In NIPS Deep Learning and Representation Learning Workshop. Geoffrey Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the Knowledge in a Neural Network. In NIPS Deep Learning and Representation Learning Workshop."},{"key":"e_1_3_2_1_10_1","volume-title":"Storkey","author":"Hospedales Timothy M.","year":"2020","unstructured":"Timothy M. Hospedales , Antreas Antoniou , Paul Micaelli , and Amos J . Storkey . 2020 . Meta-Learning in Neural Networks : A Survey . arXiv:2004.05439 (2020). Timothy M. Hospedales, Antreas Antoniou, Paul Micaelli, and Amos J. Storkey. 2020. Meta-Learning in Neural Networks: A Survey. arXiv:2004.05439 (2020)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Jeremy Howard and Sebastian Ruder. 2018. Universal Language Model Fine-tuning for Text Classification. In ACL. 328--339. Jeremy Howard and Sebastian Ruder. 2018. Universal Language Model Fine-tuning for Text Classification. In ACL. 328--339.","DOI":"10.18653\/v1\/P18-1031"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Jiayuan Huang Arthur Gretton Karsten Borgwardt Bernhard Sch\u00f6lkopf and Alex J Smola. 2007. Correcting sample selection bias by unlabeled data. In NeurIPS. 601--608. Jiayuan Huang Arthur Gretton Karsten Borgwardt Bernhard Sch\u00f6lkopf and Alex J Smola. 2007. Correcting sample selection bias by unlabeled data. In NeurIPS. 601--608.","DOI":"10.7551\/mitpress\/7503.003.0080"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Xiaoqi Jiao Yichun Yin Lifeng Shang Xin Jiang Xiao Chen Linlin Li Fang Wang and Qun Liu. 2020. TinyBERT: Distilling BERT for Natural Language Understanding. In EMNLP (Findings). 4163--4174. Xiaoqi Jiao Yichun Yin Lifeng Shang Xin Jiang Xiao Chen Linlin Li Fang Wang and Qun Liu. 2020. TinyBERT: Distilling BERT for Natural Language Understanding. In EMNLP (Findings). 4163--4174.","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Tushar Khot Ashish Sabharwal and Peter Clark. 2018. SciTaiL: A Textual Entailment Dataset from Science Question Answering. In AAAI. 5189--5197. Tushar Khot Ashish Sabharwal and Peter Clark. 2018. SciTaiL: A Textual Entailment Dataset from Science Question Answering. In AAAI. 5189--5197.","DOI":"10.1609\/aaai.v32i1.12022"},{"key":"e_1_3_2_1_15_1","volume-title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In ICLR.","author":"Lan Zhenzhong","year":"2020","unstructured":"Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , and Radu Soricut . 2020 . ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In ICLR. Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In ICLR."},{"key":"e_1_3_2_1_16_1","volume-title":"Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks. arXiv:1810.00825","author":"Lee Juho","year":"2019","unstructured":"Juho Lee , Yoonho Lee , Jungtaek Kim , Adam R. Kosiorek , Seungjin Choi , and Yee Whye Teh . 2019 . Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks. arXiv:1810.00825 (2019). Juho Lee, Yoonho Lee, Jungtaek Kim, Adam R. Kosiorek, Seungjin Choi, and Yee Whye Teh. 2019. Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks. arXiv:1810.00825 (2019)."},{"key":"e_1_3_2_1_17_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. arXiv:1910.13461","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis , Yinhan Liu , Naman Goyal , Marjan Ghazvininejad , Abdelrahman Mohamed , Omer Levy , Ves Stoyanov , and Luke Zettlemoyer . 2019 . BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. arXiv:1910.13461 (2019). Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. arXiv:1910.13461 (2019)."},{"key":"e_1_3_2_1_18_1","unstructured":"F. Li M. Qiu H. Chen X. Wang X. Gao J. Huang J. Ren Z. Zhao W. Zhao L. Wang G. Jin and W. Chu. 2017. AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experience. In CIKM. F. Li M. Qiu H. Chen X. Wang X. Gao J. Huang J. Ren Z. Zhao W. Zhao L. Wang G. Jin and W. Chu. 2017. AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experience. In CIKM."},{"key":"e_1_3_2_1_19_1","volume-title":"Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training. arXiv:1908.06066","author":"Li Gen","year":"2019","unstructured":"Gen Li , Nan Duan , Yuejian Fang , Ming Gong , Daxin Jiang , and Ming Zhou . 2019. Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training. arXiv:1908.06066 ( 2019 ). Gen Li, Nan Duan, Yuejian Fang, Ming Gong, Daxin Jiang, and Ming Zhou. 2019. Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training. arXiv:1908.06066 (2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training. arXiv preprint arXiv:1712.01887","author":"Lin Yujun","year":"2017","unstructured":"Yujun Lin , Song Han , Huizi Mao , Yu Wang , and William J Dally . 2017. Deep gradient compression: Reducing the communication bandwidth for distributed training. arXiv preprint arXiv:1712.01887 ( 2017 ). Yujun Lin, Song Han, Huizi Mao, Yu Wang, and William J Dally. 2017. Deep gradient compression: Reducing the communication bandwidth for distributed training. arXiv preprint arXiv:1712.01887 (2017)."},{"key":"e_1_3_2_1_21_1","unstructured":"Pengfei Liu Xipeng Qiu and Xuanjing Huang. 2017. Adversarial Multi-task Learning for Text Classification. In ACL. 1--10. Pengfei Liu Xipeng Qiu and Xuanjing Huang. 2017. Adversarial Multi-task Learning for Text Classification. In ACL. 1--10."},{"key":"e_1_3_2_1_22_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. 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: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:1907.11692 (2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. arXiv:1908.02265","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu , Dhruv Batra , Devi Parikh , and Stefan Lee . 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. arXiv:1908.02265 ( 2019 ). Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. arXiv:1908.02265 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Lili Mou Rui Men Ge Li Yan Xu Lu Zhang Rui Yan and Zhi Jin. 2016a. Natural Language Inference by Tree-Based Convolution and Heuristic Matching. In ACL. Lili Mou Rui Men Ge Li Yan Xu Lu Zhang Rui Yan and Zhi Jin. 2016a. Natural Language Inference by Tree-Based Convolution and Heuristic Matching. In ACL.","DOI":"10.18653\/v1\/P16-2022"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Lili Mou Zhao Meng Rui Yan Ge Li Yan Xu Lu Zhang and Zhi Jin. 2016b. How Transferable are Neural Networks in NLP Applications?. In EMNLP. Lili Mou Zhao Meng Rui Yan Ge Li Yan Xu Lu Zhang and Zhi Jin. 2016b. How Transferable are Neural Networks in NLP Applications?. In EMNLP.","DOI":"10.18653\/v1\/D16-1046"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Haojie Pan Chengyu Wang Minghui Qiu Yichang Zhang Yaliang Li and Jun Huang. 2021. Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains. In ACL\/IJCNLP. 3026--3036. Haojie Pan Chengyu Wang Minghui Qiu Yichang Zhang Yaliang Li and Jun Huang. 2021. Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains. In ACL\/IJCNLP. 3026--3036.","DOI":"10.18653\/v1\/2021.acl-long.236"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_1_28_1","volume-title":"A Comprehensive Overview and Survey of Recent Advances in Meta-Learning. arXiv:2004.11149","author":"Peng Huimin","year":"2020","unstructured":"Huimin Peng . 2020. A Comprehensive Overview and Survey of Recent Advances in Meta-Learning. arXiv:2004.11149 ( 2020 ). Huimin Peng. 2020. A Comprehensive Overview and Survey of Recent Advances in Meta-Learning. arXiv:2004.11149 (2020)."},{"key":"e_1_3_2_1_29_1","volume-title":"Sinong Wang, and Jie Tang.","author":"Qiu Jiezhong","year":"2020","unstructured":"Jiezhong Qiu , Hao Ma , Omer Levy , Scott Wen tau Yih , Sinong Wang, and Jie Tang. 2020 . Blockwise Self-Attention for Long Document Understanding . arXiv:1911.02972 (2020). Jiezhong Qiu, Hao Ma, Omer Levy, Scott Wen tau Yih, Sinong Wang, and Jie Tang. 2020. Blockwise Self-Attention for Long Document Understanding. arXiv:1911.02972 (2020)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Chen Qu Feng Ji Minghui Qiu Liu Yang Zhiyu Min Haiqing Chen Jun Huang and W Bruce Croft. 2019. Learning to selectively transfer: Reinforced transfer learning for deep text matching. In WSDM. 699--707. Chen Qu Feng Ji Minghui Qiu Liu Yang Zhiyu Min Haiqing Chen Jun Huang and W Bruce Croft. 2019. Learning to selectively transfer: Reinforced transfer learning for deep text matching. In WSDM. 699--707.","DOI":"10.1145\/3289600.3290978"},{"key":"e_1_3_2_1_31_1","volume-title":"Improving language understanding by generative pre-training. arXiv","author":"Radford Alec","year":"2018","unstructured":"Alec Radford , Karthik Narasimhan , Tim Salimans , and Ilya Sutskever . 2018. Improving language understanding by generative pre-training. arXiv ( 2018 ). Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. arXiv (2018)."},{"key":"e_1_3_2_1_32_1","volume-title":"Language models are unsupervised multitask learners. OpenAI blog","author":"Radford Alec","year":"2019","unstructured":"Alec Radford , Jeffrey Wu , Rewon Child , David Luan , Dario Amodei , and Ilya Sutskever . 2019. Language models are unsupervised multitask learners. OpenAI blog , Vol. 1 , 8 ( 2019 ), 9. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog, Vol. 1, 8 (2019), 9."},{"key":"e_1_3_2_1_33_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 , and Peter J. Liu . 2020 . Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer . J. Mach. Learn. Res. , Vol. 21 (2020), 140:1--140:67. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. J. Mach. Learn. Res., Vol. 21 (2020), 140:1--140:67.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_34_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2015","unstructured":"Adriana Romero , Nicolas Ballas , Samira Ebrahimi Kahou , Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015 . FitNets: Hints for Thin Deep Nets. In ICLR. Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015. FitNets: Hints for Thin Deep Nets. In ICLR."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Sebastian Ruder and Barbara Plank. 2017. Learning to select data for transfer learning with Bayesian Optimization. In EMNLP. 372--382. Sebastian Ruder and Barbara Plank. 2017. Learning to select data for transfer learning with Bayesian Optimization. In EMNLP. 372--382.","DOI":"10.18653\/v1\/D17-1038"},{"key":"e_1_3_2_1_36_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv","author":"Sanh Victor","year":"1910","unstructured":"Victor Sanh , Lysandre Debut , Julien Chaumond , and Thomas Wolf . 2019. DistilBERT , a distilled version of BERT: smaller, faster, cheaper and lighter. 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: 1910.01108 (2019)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00162"},{"key":"e_1_3_2_1_38_1","unstructured":"Noam Shazeer Azalia Mirhoseini Krzysztof Maziarz Andy Davis Quoc Le Geoffrey Hinton and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. arxiv: 1701.06538 [cs.LG] Noam Shazeer Azalia Mirhoseini Krzysztof Maziarz Andy Davis Quoc Le Geoffrey Hinton and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. arxiv: 1701.06538 [cs.LG]"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Jian Shen Yanru Qu Weinan Zhang and Yong Yu. 2018. Wasserstein Distance Guided Representation Learning for Domain Adaptation. In AAAI. 4058--4065. Jian Shen Yanru Qu Weinan Zhang and Yong Yu. 2018. Wasserstein Distance Guided Representation Learning for Domain Adaptation. In AAAI. 4058--4065.","DOI":"10.1609\/aaai.v32i1.11784"},{"key":"e_1_3_2_1_40_1","volume-title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations. arXiv:1908.08530","author":"Su Weijie","year":"2020","unstructured":"Weijie Su , Xizhou Zhu , Yue Cao , Bin Li , Lewei Lu , Furu Wei , and Jifeng Dai . 2020. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. arXiv:1908.08530 ( 2020 ). Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. 2020. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. arXiv:1908.08530 (2020)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Siqi Sun Yu Cheng Zhe Gan and Jingjing Liu. 2019. Patient Knowledge Distillation for BERT Model Compression. In EMNLP-IJCNLP. 4322--4331. Siqi Sun Yu Cheng Zhe Gan and Jingjing Liu. 2019. Patient Knowledge Distillation for BERT Model Compression. In EMNLP-IJCNLP. 4322--4331.","DOI":"10.18653\/v1\/D19-1441"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Chuanqi Tan Fuchun Sun Tao Kong Wenchang Zhang Chao Yang and Chunfang Liu. 2018. A Survey on Deep Transfer Learning. In ICANN. 270--279. Chuanqi Tan Fuchun Sun Tao Kong Wenchang Zhang Chao Yang and Chunfang Liu. 2018. A Survey on Deep Transfer Learning. In ICANN. 270--279.","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"e_1_3_2_1_43_1","volume-title":"Distilling Task-Specific Knowledge from BERT into Simple Neural Networks. arXiv","author":"Tang Raphael","year":"1903","unstructured":"Raphael Tang , Yao Lu , Linqing Liu , Lili Mou , Olga Vechtomova , and Jimmy Lin . 2019. Distilling Task-Specific Knowledge from BERT into Simple Neural Networks. arXiv : 1903 .12136 (2019). Raphael Tang, Yao Lu, Linqing Liu, Lili Mou, Olga Vechtomova, and Jimmy Lin. 2019. Distilling Task-Specific Knowledge from BERT into Simple Neural Networks. arXiv: 1903.12136 (2019)."},{"key":"e_1_3_2_1_44_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In NIPS. 5998--6008. Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In NIPS. 5998--6008."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"B. Wang M. Qiu X. Wang Y. Li Y. Gong X. Zeng J. Huang B. Zheng D. Cai and J. Zhou. 2019. A Minimax Game for Instance based Selective Transfer Learning. In SIGKDD. B. Wang M. Qiu X. Wang Y. Li Y. Gong X. Zeng J. Huang B. Zheng D. Cai and J. Zhou. 2019. A Minimax Game for Instance based Selective Transfer Learning. In SIGKDD.","DOI":"10.1145\/3292500.3330841"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"C. Wang M. Qiu J. Huang and X. He. 2020 b. Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining. In EMNLP. C. Wang M. Qiu J. Huang and X. He. 2020 b. Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining. In EMNLP.","DOI":"10.18653\/v1\/2020.emnlp-main.250"},{"key":"e_1_3_2_1_47_1","volume-title":"2020 a. Linformer: Self-Attention with Linear Complexity. arXiv:2006.04768","author":"Wang Sinong","year":"2020","unstructured":"Sinong Wang , Belinda Z. Li , Madian Khabsa , Han Fang , and Hao Ma . 2020 a. Linformer: Self-Attention with Linear Complexity. arXiv:2006.04768 ( 2020 ). Sinong Wang, Belinda Z. Li, Madian Khabsa, Han Fang, and Hao Ma. 2020 a. Linformer: Self-Attention with Linear Complexity. arXiv:2006.04768 (2020)."},{"key":"e_1_3_2_1_48_1","volume-title":"Bowman","author":"Williams Adina","year":"2018","unstructured":"Adina Williams , Nikita Nangia , and Samuel R . Bowman . 2018 . A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference. In NAACL. Adina Williams, Nikita Nangia, and Samuel R. Bowman. 2018. A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference. In NAACL."},{"key":"e_1_3_2_1_49_1","volume-title":"Cohen","author":"Yang Zhilin","year":"2017","unstructured":"Zhilin Yang , Ruslan Salakhutdinov , and William W . Cohen . 2017 . Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks. In ICLR. Zhilin Yang, Ruslan Salakhutdinov, and William W. Cohen. 2017. Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks. In ICLR."},{"key":"e_1_3_2_1_50_1","unstructured":"Jianfei Yu Minghui Qiu Jing Jiang Jun Huang Shuangyong Song Wei Chu and Haiqing Chen. 2018. Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce. In WSDM. Jianfei Yu Minghui Qiu Jing Jiang Jun Huang Shuangyong Song Wei Chu and Haiqing Chen. 2018. Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce. In WSDM."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.14778\/2733004.2733012"},{"key":"e_1_3_2_1_52_1","volume-title":"Fusionstitching: boosting memory intensive computations for deep learning workloads. arXiv:2009.10924","author":"Zheng Zhen","year":"2020","unstructured":"Zhen Zheng , Pengzhan Zhao , Guoping Long , Feiwen Zhu , Kai Zhu , Wenyi Zhao , Lansong Diao , Jun Yang , and Wei Lin . 2020. Fusionstitching: boosting memory intensive computations for deep learning workloads. arXiv:2009.10924 ( 2020 ). Zhen Zheng, Pengzhan Zhao, Guoping Long, Feiwen Zhu, Kai Zhu, Wenyi Zhao, Lansong Diao, Jun Yang, and Wei Lin. 2020. Fusionstitching: boosting memory intensive computations for deep learning workloads. arXiv:2009.10924 (2020)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Fuzhen Zhuang Lang Huang Jia He Jixin Ma and Qing He. 2017. Transfer Learning with Manifold Regularized Convolutional Neural Network. In KSEM. Fuzhen Zhuang Lang Huang Jia He Jixin Ma and Qing He. 2017. Transfer Learning with Manifold Regularized Convolutional Neural Network. In KSEM.","DOI":"10.1007\/978-3-319-63558-3_41"},{"key":"e_1_3_2_1_54_1","volume-title":"A Comprehensive Survey on Transfer Learning. arXiv:1911.02685","author":"Zhuang Fuzhen","year":"2019","unstructured":"Fuzhen Zhuang , Zhiyuan Qi , Keyu Duan , Dongbo Xi , Yongchun Zhu , Hengshu Zhu , Hui Xiong , and Qing He. 2019. A Comprehensive Survey on Transfer Learning. arXiv:1911.02685 ( 2019 ). Fuzhen Zhuang, Zhiyuan Qi, Keyu Duan, Dongbo Xi, Yongchun Zhu, Hengshu Zhu, Hui Xiong, and Qing He. 2019. A Comprehensive Survey on Transfer Learning. arXiv:1911.02685 (2019)."}],"event":{"name":"CIKM '21: The 30th ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Virtual Event Queensland Australia","acronym":"CIKM '21"},"container-title":["Proceedings of the 30th ACM International Conference on Information & Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3481911","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3459637.3481911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:58Z","timestamp":1750193338000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3459637.3481911"}},"subtitle":["A Simple and Scalable Deep Transfer Learning Platform for NLP Applications"],"short-title":[],"issued":{"date-parts":[[2021,10,26]]},"references-count":54,"alternative-id":["10.1145\/3459637.3481911","10.1145\/3459637"],"URL":"https:\/\/doi.org\/10.1145\/3459637.3481911","relation":{},"subject":[],"published":{"date-parts":[[2021,10,26]]},"assertion":[{"value":"2021-10-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}