{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T12:39:02Z","timestamp":1763728742958},"reference-count":103,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T00:00:00Z","timestamp":1714953600000},"content-version":"vor","delay-in-days":126,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>In many NLP applications, to mitigate data deficiency in a target task, source data is collected to help with target model training. Existing transfer learning methods either select a subset of source examples that are close to the target domain or try to adapt all source examples into the target domain, then use selected or adapted source examples to train the target model. These methods either incur significant information loss or bear the risk that after adaptation, source examples which are originally already in the target domain may be outside the target domain. To address the limitations of these methods, we propose a four-level optimization based framework which simultaneously selects and adapts source data. Our method can automatically identify in-domain and out-of-domain source examples and apply example-specific processing methods: selection for in-domain examples and adaptation for out-of-domain examples. Experiments on various datasets demonstrate the effectiveness of our proposed method.<\/jats:p>","DOI":"10.1162\/tacl_a_00658","type":"journal-article","created":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T20:13:36Z","timestamp":1715026416000},"page":"449-466","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":1,"title":["Simultaneous Selection and Adaptation of Source Data via Four-Level Optimization"],"prefix":"10.1162","volume":"12","author":[{"given":"Pengtao","family":"Xie","sequence":"first","affiliation":[{"name":"UC San Diego, USA. p1xie@ucsd.edu"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingchen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Northeastern University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuehai","family":"He","sequence":"additional","affiliation":[{"name":"UC Santa Cruz, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2024,5,3]]},"reference":[{"key":"2024050620131513800_bib1","first-page":"355","article-title":"Domain adaptation via pseudo in-domain data selection","volume-title":"Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing","author":"Axelrod","year":"2011"},{"key":"2024050620131513800_bib2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59710-8_48","article-title":"Source-relaxed domain adaptation for image segmentation","author":"Bateson","year":"2020","journal-title":"CoRR"},{"key":"2024050620131513800_bib3","article-title":"Online learning rate adaptation with hypergradient descent","author":"Baydin","year":"2017","journal-title":"CoRR"},{"issue":"1","key":"2024050620131513800_bib4","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10994-009-5152-4","article-title":"A theory of learning from different domains","volume":"79","author":"Ben-David","year":"2010","journal-title":"Machine Learning"},{"issue":"14","key":"2024050620131513800_bib5","doi-asserted-by":"publisher","first-page":"e49\u2013e57","DOI":"10.1093\/bioinformatics\/btl242","article-title":"Integrating structured biological data by kernel maximum mean discrepancy","volume":"22","author":"Borgwardt","year":"2006","journal-title":"Bioinformatics"},{"key":"2024050620131513800_bib6","doi-asserted-by":"publisher","first-page":"3722","DOI":"10.1109\/CVPR.2017.18","article-title":"Unsupervised pixel-level domain adaptation with generative adversarial networks","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Bousmalis","year":"2017"},{"key":"2024050620131513800_bib7","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"arXiv preprint arXiv:2002.05709"},{"key":"2024050620131513800_bib8","article-title":"Reducing overfitting in deep networks by decorrelating representations","author":"Cogswell","year":"2015","journal-title":"arXiv preprint arXiv:1511.06068"},{"key":"2024050620131513800_bib9","first-page":"308","article-title":"PubMed 200k RCT: A dataset for sequential sentence classification in medical abstracts","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)","author":"Dernoncourt","year":"2017"},{"issue":"3","key":"2024050620131513800_bib10","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TNNLS.2011.2178556","article-title":"Domain adaptation from multiple sources: A domain-dependent regularization approach","volume":"23","author":"Duan","year":"2012","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2024050620131513800_bib11","doi-asserted-by":"publisher","first-page":"2163","DOI":"10.18653\/v1\/D19-1222","article-title":"To annotate or not? Predicting performance drop under domain shift","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Elsahar","year":"2019"},{"key":"2024050620131513800_bib12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9354","article-title":"Initializing Bayesian hyperparameter optimization via meta-learning","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Feurer","year":"2015"},{"key":"2024050620131513800_bib13","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70","author":"Finn","year":"2017"},{"key":"2024050620131513800_bib14","first-page":"451","article-title":"Discriminative instance weighting for domain adaptation in statistical machine translation","volume-title":"Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing","author":"Foster","year":"2010"},{"issue":"1","key":"2024050620131513800_bib15","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"2024050620131513800_bib16","doi-asserted-by":"publisher","first-page":"6894","DOI":"10.18653\/v1\/2021.emnlp-main.552","article-title":"SimCSE: Simple contrastive learning of sentence embeddings","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Gao","year":"2021"},{"key":"2024050620131513800_bib17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.9","article-title":"Borrowing treasures from the wealthy: Deep transfer learning through selective joint fine-tuning","author":"Ge","year":"2017","journal-title":"CoRR"},{"key":"2024050620131513800_bib18","article-title":"Approximation methods for bilevel programming","author":"Ghadimi","year":"2018","journal-title":"arXiv preprint arXiv:1802.02246"},{"key":"2024050620131513800_bib19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31865-1_25","article-title":"A probabilistic interpretation of precision, recall and f-score, with implication for evaluation","volume-title":"European Conference on Information Retrieval","author":"Goutte","year":"2005"},{"key":"2024050620131513800_bib20","first-page":"3748","article-title":"On the iteration complexity of hypergradient computation","volume-title":"International Conference on Machine Learning","author":"Grazzi","year":"2020"},{"key":"2024050620131513800_bib21","article-title":"Autosem: Automatic task selection and mixing in multi-task learning","author":"Guo","year":"2019","journal-title":"CoRR"},{"key":"2024050620131513800_bib22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740","article-title":"Don\u2019t stop pretraining: Adapt language models to domains and tasks","volume-title":"Proceedings of ACL","author":"Gururangan","year":"2020"},{"key":"2024050620131513800_bib23","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2019","journal-title":"arXiv preprint arXiv:1911.05722"},{"key":"2024050620131513800_bib24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","volume-title":"CVPR","author":"He","year":"2016"},{"key":"2024050620131513800_bib25","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883037","article-title":"Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering","volume-title":"WWW","author":"He","year":"2016"},{"key":"2024050620131513800_bib26","article-title":"Pathvqa: 30000+ questions for medical visual question answering","author":"He","year":"2020","journal-title":"arXiv preprint arXiv:2003.10286"},{"key":"2024050620131513800_bib27","first-page":"1989","article-title":"Cycada: Cycle-consistent adversarial domain adaptation","volume-title":"International Conference on Machine Learning","author":"Hoffman","year":"2018"},{"key":"2024050620131513800_bib28","article-title":"Learning data manipulation for augmentation and weighting","author":"Zhiting","year":"2019","journal-title":"CoRR"},{"key":"2024050620131513800_bib29","doi-asserted-by":"publisher","first-page":"1950","DOI":"10.1145\/3404835.3462992","article-title":"Learning to select instance: Simultaneous transfer learning and clustering","volume-title":"Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Huan","year":"2021"},{"key":"2024050620131513800_bib30","doi-asserted-by":"publisher","first-page":"601","DOI":"10.7551\/mitpress\/7503.003.0080","article-title":"Correcting sample selection bias by unlabeled data","volume":"19","author":"Huang","year":"2006","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024050620131513800_bib31","article-title":"Categorical reparametrization with gumble-softmax","volume-title":"International Conference on Learning Representations (ICLR 2017)","author":"Jang","year":"2017"},{"key":"2024050620131513800_bib32","first-page":"4882","article-title":"Bilevel optimization: Convergence analysis and enhanced design","volume-title":"International Conference on Machine Learning","author":"Ji","year":"2021"},{"key":"2024050620131513800_bib33","article-title":"Instance weighting for domain adaptation in nlp","author":"Jiang","year":"2007"},{"key":"2024050620131513800_bib34","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00028","article-title":"Measuring the evolution of a scientific field through citation frames","author":"Jurgens","year":"2018","journal-title":"TACL"},{"key":"2024050620131513800_bib35","doi-asserted-by":"publisher","first-page":"4893","DOI":"10.1109\/CVPR.2019.00503","article-title":"Contrastive adaptation network for unsupervised domain adaptation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Kang","year":"2019"},{"key":"2024050620131513800_bib36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S19-2145","article-title":"SemEval-2019 Task 4: Hyperpartisan news detection","volume-title":"SemEval","author":"Kiesel","year":"2019"},{"key":"2024050620131513800_bib37","article-title":"Bilinear attention networks","volume-title":"NIPS","author":"Kim","year":"2018"},{"key":"2024050620131513800_bib38","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58568-6_35","article-title":"Attract, perturb, and explore: Learning a feature alignment network for semi-supervised domain adaptation","author":"Kim","year":"2020"},{"key":"2024050620131513800_bib39","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"2024050620131513800_bib40","doi-asserted-by":"publisher","DOI":"10.1093\/database\/bav123","article-title":"ChemProt-3.0: A global chemical biology diseases mapping","volume-title":"Database","author":"Kringelum","year":"2016"},{"key":"2024050620131513800_bib41","doi-asserted-by":"publisher","first-page":"16632","DOI":"10.1109\/CVPR46437.2021.01636","article-title":"Domain adaptation with auxiliary target domain-oriented classifier","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liang","year":"2021"},{"key":"2024050620131513800_bib42","article-title":"Darts: Differentiable architecture search","author":"Liu","year":"2018","journal-title":"arXiv preprint arXiv:1806.09055"},{"key":"2024050620131513800_bib43","first-page":"4013","article-title":"Transferable adversarial training: A general approach to adapting deep classifiers","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Liu","year":"2019"},{"key":"2024050620131513800_bib44","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1189","article-title":"Reinforced training data selection for domain adaptation","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Liu","year":"2019"},{"key":"2024050620131513800_bib45","article-title":"Towards gradient-based bilevel optimization with non-convex followers and beyond","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024050620131513800_bib46","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv:1907.11692"},{"key":"2024050620131513800_bib47","article-title":"S2orc: The semantic scholar open research corpus","author":"Lo","year":"2019","journal-title":"arXiv preprint arXiv:1911.02782"},{"key":"2024050620131513800_bib48","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","volume-title":"International Conference on Machine Learning","author":"Long","year":"2015"},{"key":"2024050620131513800_bib49","article-title":"Conditional adversarial domain adaptation","author":"Long","year":"2017","journal-title":"arXiv preprint arXiv:1705.10667"},{"key":"2024050620131513800_bib50","doi-asserted-by":"publisher","first-page":"2200","DOI":"10.1109\/ICCV.2013.274","article-title":"Transfer feature learning with joint distribution adaptation","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Long","year":"2013"},{"key":"2024050620131513800_bib51","first-page":"2208","article-title":"Deep transfer learning with joint adaptation networks","volume-title":"International conference on machine learning","author":"Long","year":"2017"},{"key":"2024050620131513800_bib52","article-title":"Fixing weight decay regularization in Adam","author":"Loshchilov","year":"2017","journal-title":"ArXiv"},{"key":"2024050620131513800_bib53","doi-asserted-by":"publisher","first-page":"3219","DOI":"10.18653\/v1\/D18-1360","article-title":"Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Yi","year":"2018"},{"key":"2024050620131513800_bib54","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/1458082.1458099","article-title":"Transfer learning from multiple source domains via consensus regularization","volume-title":"Proceedings of the 17th ACM Conference on Information and Knowledge Management","author":"Luo","year":"2008"},{"key":"2024050620131513800_bib55","article-title":"Label efficient learning of transferable representations across domains and tasks","author":"Luo","year":"2017","journal-title":"arXiv preprint arXiv:1712.00123"},{"key":"2024050620131513800_bib56","article-title":"Learning word vectors for sentiment analysis","volume-title":"ACL","author":"Maas","year":"2011"},{"key":"2024050620131513800_bib57","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume-title":"NIPS","author":"Malinowski","year":"2014"},{"key":"2024050620131513800_bib58","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755","article-title":"Image-based recommendations on styles and substitutes","volume-title":"ACM SIGIR","author":"McAuley","year":"2015"},{"key":"2024050620131513800_bib59","article-title":"Mixed precision training","author":"Micikevicius","year":"2017","journal-title":"arXiv preprint arXiv:1710.03740"},{"key":"2024050620131513800_bib60","first-page":"608","article-title":"Mapping and revising markov logic networks for transfer learning","volume-title":"Proceedings of AAAI","author":"Mihalkova","year":"2007"},{"key":"2024050620131513800_bib61","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1109\/CVPR46437.2021.00114","article-title":"Generalized domain adaptation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Mitsuzumi","year":"2021"},{"key":"2024050620131513800_bib62","doi-asserted-by":"publisher","DOI":"10.5005\/jp\/books\/12412","volume-title":"Textbook of Pathology","author":"Mohan","year":"2015"},{"key":"2024050620131513800_bib63","article-title":"Intelligent selection of language model training data","author":"Moore","year":"2010"},{"key":"2024050620131513800_bib64","article-title":"Few-shot adversarial domain adaptation","volume":"30","author":"Motiian","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024050620131513800_bib65","article-title":"Domain adaptive transfer learning with specialist models","author":"Ngiam","year":"2018","journal-title":"arXiv preprint arXiv:1811.07056"},{"key":"2024050620131513800_bib66","first-page":"339","article-title":"Inductive transfer for Bayesian network structure learning","volume-title":"Artificial Intelligence and Statistics","author":"Niculescu-Mizil","year":"2007"},{"issue":"2","key":"2024050620131513800_bib67","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1109\/TNN.2010.2091281","article-title":"Domain adaptation via transfer component analysis","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"10","key":"2024050620131513800_bib68","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2009","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2024050620131513800_bib69","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"ACL","author":"Papineni","year":"2002"},{"key":"2024050620131513800_bib70","article-title":"Learning sampling policies for domain adaptation","author":"Patel","year":"2018","journal-title":"CoRR"},{"key":"2024050620131513800_bib71","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162","article-title":"GloVe: Global vectors for word representation","volume-title":"EMNLP","author":"Pennington","year":"2014"},{"key":"2024050620131513800_bib72","first-page":"204","article-title":"Discriminability-based transfer between neural networks","author":"Pratt","year":"1993","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024050620131513800_bib73","article-title":"Learning to selectively transfer: Reinforced transfer learning for deep text matching","author":"Chen","year":"2018","journal-title":"CoRR"},{"key":"2024050620131513800_bib74","article-title":"Learning to reweight examples for robust deep learning","author":"Ren","year":"2018","journal-title":"arXiv preprint arXiv:1803.09050"},{"key":"2024050620131513800_bib75","first-page":"21786","article-title":"Not all unlabeled data are equal: Learning to weight data in semi-supervised learning","volume-title":"Advances in Neural Information Processing Systems","author":"Ren","year":"2020"},{"key":"2024050620131513800_bib76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1038","article-title":"Learning to select data for transfer learning with bayesian optimization","author":"Ruder","year":"2017","journal-title":"CoRR"},{"key":"2024050620131513800_bib77","doi-asserted-by":"publisher","first-page":"8050","DOI":"10.1109\/ICCV.2019.00814","article-title":"Semi-supervised domain adaptation via minimax entropy","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Saito","year":"2019"},{"key":"2024050620131513800_bib78","doi-asserted-by":"publisher","first-page":"8503","DOI":"10.1109\/CVPR.2018.00887","article-title":"Generate to adapt: Aligning domains using generative adversarial networks","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Sankaranarayanan","year":"2018"},{"key":"2024050620131513800_bib79","first-page":"1919","article-title":"Meta-weight-net: Learning an explicit mapping for sample weighting","volume-title":"Advances in Neural Information Processing Systems","author":"Shu","year":"2019"},{"key":"2024050620131513800_bib80","doi-asserted-by":"publisher","first-page":"4885","DOI":"10.1109\/ICASSP.2017.7953085","article-title":"Discriminative importance weighting of augmented training data for acoustic model training","volume-title":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Sivasankaran","year":"2017"},{"key":"2024050620131513800_bib81","first-page":"1191","article-title":"Entropy-based training data selection for domain adaptation","volume-title":"Proceedings of COLING 2012: Posters","author":"Song","year":"2012"},{"key":"2024050620131513800_bib82","article-title":"Generative teaching networks: Accelerating neural architecture search by learning to generate synthetic training data","author":"Such","year":"2019","journal-title":"CoRR"},{"key":"2024050620131513800_bib83","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/978-3-319-49409-8_35","article-title":"Deep coral: Correlation alignment for deep domain adaptation","volume-title":"European Conference on Computer Vision","author":"Sun","year":"2016"},{"key":"2024050620131513800_bib84","first-page":"505","article-title":"A two-stage weighting framework for multi-source domain adaptation","volume":"24","author":"Sun","year":"2011","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024050620131513800_bib85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514","article-title":"Lxmert: Learning cross-modality encoder representations from transformers","author":"Tan","year":"2019","journal-title":"arXiv preprint arXiv:1908.07490"},{"key":"2024050620131513800_bib86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00875","article-title":"Unsupervised domain adaptation via structurally regularized deep clustering","author":"Tang","year":"2020"},{"key":"2024050620131513800_bib87","article-title":"Discriminative adversarial domain adaptation","author":"Tang","year":"2019","journal-title":"CoRR"},{"key":"2024050620131513800_bib88","doi-asserted-by":"publisher","first-page":"3081","DOI":"10.1109\/CVPR.2010.5540064","article-title":"Safety in numbers: Learning categories from few examples with multi model knowledge transfer","volume-title":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition","author":"Tommasi","year":"2010"},{"key":"2024050620131513800_bib89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316","article-title":"Adversarial discriminative domain adaptation","author":"Tzeng","year":"2017"},{"key":"2024050620131513800_bib90","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"2024050620131513800_bib91","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330841","article-title":"A minimax game for instance based selective transfer learning","author":"Wang","year":"2019","journal-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"2024050620131513800_bib92","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1109\/ICDM.2017.150","article-title":"Balanced distribution adaptation for transfer learning","volume-title":"2017 IEEE International Conference on Data Mining (ICDM)","author":"Wang","year":"2017"},{"key":"2024050620131513800_bib93","doi-asserted-by":"publisher","first-page":"1482","DOI":"10.18653\/v1\/D17-1155","article-title":"Instance weighting for neural machine translation domain adaptation","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Wang","year":"2017"},{"key":"2024050620131513800_bib94","first-page":"9983","article-title":"Optimizing data usage via differentiable rewards","volume-title":"International Conference on Machine Learning","author":"Wang","year":"2020"},{"key":"2024050620131513800_bib95","article-title":"Meta-semi: A meta-learning approach for semi-supervised learning","volume":"abs\/2007.02394","author":"Wang","year":"2020","journal-title":"CoRR"},{"key":"2024050620131513800_bib96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-26142-9_9","article-title":"The most related knowledge first: A progressive domain adaptation method","volume-title":"PAKDD","author":"Wang","year":"2019"},{"key":"2024050620131513800_bib97","article-title":"Provably faster algorithms for bilevel optimization","volume":"34","author":"Yang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024050620131513800_bib98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10","article-title":"Stacked attention networks for image question answering","volume-title":"CVPR","author":"Yang","year":"2016"},{"key":"2024050620131513800_bib99","article-title":"Defending against neural fake news","volume":"32","author":"Zellers","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024050620131513800_bib100","article-title":"Character-level convolutional networks for text classification","volume-title":"NeurIPS","author":"Zhang","year":"2015"},{"key":"2024050620131513800_bib101","doi-asserted-by":"publisher","first-page":"5031","DOI":"10.1109\/CVPR.2019.00517","article-title":"Domain-symmetric networks for adversarial domain adaptation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhang","year":"2019"},{"key":"2024050620131513800_bib102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.223","article-title":"Curriculum domain adaptation for semantic segmentation of urban scenes","author":"Zhang","year":"2017","journal-title":"CoRR"},{"issue":"1","key":"2024050620131513800_bib103","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A comprehensive survey on transfer learning","volume":"109","author":"Zhuang","year":"2020","journal-title":"Proceedings of the IEEE"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00658\/2369515\/tacl_a_00658.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00658\/2369515\/tacl_a_00658.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,6]],"date-time":"2024-05-06T20:15:03Z","timestamp":1715026503000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00658\/120912\/Simultaneous-Selection-and-Adaptation-of-Source"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":103,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00658","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024]]},"published":{"date-parts":[[2024]]}}}