{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T22:12:46Z","timestamp":1769724766212,"version":"3.49.0"},"reference-count":70,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2018,10,29]],"date-time":"2018-10-29T00:00:00Z","timestamp":1540771200000},"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":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2018,11,30]]},"abstract":"<jats:p>Learning from very few samples is a challenge for machine learning tasks, such as text and image classification. Performance of such task can be enhanced via transfer of helpful knowledge from related domains, which is referred to as transfer learning. In previous transfer learning works, instance transfer learning algorithms mostly focus on selecting the source domain instances similar to the target domain instances for transfer. However, the selected instances usually do not directly contribute to the learning performance in the target domain. Hypothesis transfer learning algorithms focus on the model\/parameter level transfer. They treat the source hypotheses as well-trained and transfer their knowledge in terms of parameters to learn the target hypothesis. Such algorithms directly optimize the target hypothesis by the observable performance improvements. However, they fail to consider the problem that instances that contribute to the source hypotheses may be harmful for the target hypothesis, as instance transfer learning analyzed. To relieve the aforementioned problems, we propose a novel transfer learning algorithm, which follows an analogical strategy. Particularly, the proposed algorithm first learns a revised source hypothesis with only instances contributing to the target hypothesis. Then, the proposed algorithm transfers both the revised source hypothesis and the target hypothesis (only trained with a few samples) to learn an analogical hypothesis. We denote our algorithm as Analogical Transfer Learning. Extensive experiments on one synthetic dataset and three real-world benchmark datasets demonstrate the superior performance of the proposed algorithm.<\/jats:p>","DOI":"10.1145\/3230709","type":"journal-article","created":{"date-parts":[[2018,10,29]],"date-time":"2018-10-29T12:02:18Z","timestamp":1540814538000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Few-Shot Text and Image Classification via Analogical Transfer Learning"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4679-2958","authenticated-orcid":false,"given":"Wenhe","family":"Liu","sequence":"first","affiliation":[{"name":"University of Technology Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"Texas State University, San Marcos, TX"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander G.","family":"Hauptmann","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pennsylvania, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,10,29]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Ling","author":"Ao Shuang","year":"2017"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126504"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273507"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.57"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2708506"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2910585"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582746"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2608901"},{"key":"e_1_2_1_10_1","volume-title":"AAAI Conference on Artificial Intelligence.","author":"Choi Jonghyun"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273521"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2821921"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2631887"},{"key":"e_1_2_1_14_1","volume-title":"AAAI Conference on Artificial Intelligence","volume":"3","author":"Fan Yanbo","year":"2017"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2413789"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2281420"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401928"},{"key":"e_1_2_1_18_1","unstructured":"Peter G\u00e4rdenfors. 2003. Belief Revision. Vol. 29. Cambridge University Press.   Peter G\u00e4rdenfors. 2003. Belief Revision. Vol. 29. Cambridge University Press."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/sam.11217"},{"key":"e_1_2_1_20_1","volume-title":"AAAI Conference on Artificial Intelligence. 1831--1839","author":"G\u00f6nen Mehmet","year":"2014"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/5254.708428"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383295"},{"key":"e_1_2_1_23_1","volume-title":"Efficient learning of domain-invariant image representations. arXiv preprint arXiv:1301.3224","author":"Hoffman Judy","year":"2013"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2609820"},{"key":"e_1_2_1_25_1","volume-title":"Smola","author":"Huang Jiayuan","year":"2007"},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of the Annual Meeting on Association for Computational Linguistics","volume":"7","author":"Jiang Jing","year":"2007"},{"key":"e_1_2_1_27_1","unstructured":"Lu Jiang Deyu Meng Shoou-I Yu Zhenzhong Lan Shiguang Shan and Alexander Hauptmann. 2014. Self-paced learning with diversity. In Advances in Neural Information Processing Systems. 2078--2086.   Lu Jiang Deyu Meng Shoou-I Yu Zhenzhong Lan Shiguang Shan and Alexander Hauptmann. 2014. Self-paced learning with diversity. In Advances in Neural Information Processing Systems. 2078--2086."},{"key":"e_1_2_1_28_1","volume-title":"AAAI Conference on Artificial Intelligence","volume":"2","author":"Jiang Lu"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2644866"},{"key":"e_1_2_1_30_1","volume-title":"Semi-Supervised Learning","author":"Chapelle Olivier","edition":"1"},{"key":"e_1_2_1_31_1","volume-title":"Hierarchical active transfer learning","author":"Kale David"},{"key":"e_1_2_1_32_1","unstructured":"M. Pawan Kumar Benjamin Packer and Daphne Koller. 2010. Self-paced learning for latent variable models. In Advances in Neural Information Processing Systems. 1189--1197.   M. Pawan Kumar Benjamin Packer and Daphne Koller. 2010. Self-paced learning for latent variable models. In Advances in Neural Information Processing Systems. 1189--1197."},{"key":"e_1_2_1_33_1","volume-title":"Proceedings of the International Conference on Machine Learning. 942--950","author":"Kuzborskij Ilja","year":"2013"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5594-4"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.431"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.09.003"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3091622.3091662"},{"key":"e_1_2_1_38_1","article-title":"Rcv1: A new benchmark collection for text categorization research","author":"Lewis David D.","year":"2004","journal-title":"Journal of Machine Learning Research 5"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2728531"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2829867"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102415"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2544314"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2373376"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2659221"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1076"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123313"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/1703435.1703507"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Joaquin Quionero-Candela Masashi Sugiyama Anton Schwaighofer and Neil D. Lawrence. 2009. Dataset Shift in Machine Learning. The MIT Press.   Joaquin Quionero-Candela Masashi Sugiyama Anton Schwaighofer and Neil D. Lawrence. 2009. Dataset Shift in Machine Learning. The MIT Press.","DOI":"10.7551\/mitpress\/9780262170055.001.0001"},{"key":"e_1_2_1_50_1","volume-title":"International Conference on Learning Representations.","author":"Ravi Sachin","year":"2017"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2365725"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2011.73"},{"key":"e_1_2_1_53_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.  Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"e_1_2_1_54_1","volume-title":"Zemel","author":"Snell Jake","year":"2017"},{"key":"e_1_2_1_55_1","unstructured":"Richard Socher Milind Ganjoo Christopher D. Manning and Andrew Ng. 2013. Zero-shot learning through cross-modal transfer. In Advances in Neural Information Processing Systems. 935--943.   Richard Socher Milind Ganjoo Christopher D. Manning and Andrew Ng. 2013. Zero-shot learning through cross-modal transfer. In Advances in Neural Information Processing Systems. 935--943."},{"key":"e_1_2_1_56_1","unstructured":"Masashi Sugiyama Shinichi Nakajima Hisashi Kashima Paul V. Buenau and Motoaki Kawanabe. 2008. Direct importance estimation with model selection and its application to covariate shift adaptation. In Advances in Neural Information Processing Systems. 1433--1440.   Masashi Sugiyama Shinichi Nakajima Hisashi Kashima Paul V. Buenau and Motoaki Kawanabe. 2008. Direct importance estimation with model selection and its application to covariate shift adaptation. In Advances in Neural Information Processing Systems. 1433--1440."},{"key":"e_1_2_1_57_1","volume-title":"Hospedales","author":"Sung Flood","year":"2017"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.308"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540064"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.197"},{"key":"e_1_2_1_61_1","unstructured":"Oriol Vinyals Charles Blundell Tim Lillicrap Daan Wierstra etal 2016. Matching networks for one shot learning. In Advances in Neural Information Processing Systems. 3630--3638.   Oriol Vinyals Charles Blundell Tim Lillicrap Daan Wierstra et al. 2016. Matching networks for one shot learning. In Advances in Neural Information Processing Systems. 3630--3638."},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2605687"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3003729"},{"key":"e_1_2_1_64_1","volume-title":"AAAI Conference on Artificial Intelligence.","author":"Wang Yu-Xiong","year":"2016"},{"key":"e_1_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Yongqin Xian Christoph H. Lampert Bernt Schiele and Zeynep Akata. 2017. Zero-shot learning\u2014A comprehensive evaluation of the good the bad and the ugly. arXiv preprint arXiv:1707.00600.  Yongqin Xian Christoph H. Lampert Bernt Schiele and Zeynep Akata. 2017. Zero-shot learning\u2014A comprehensive evaluation of the good the bad and the ugly. arXiv preprint arXiv:1707.00600.","DOI":"10.1109\/CVPR.2017.328"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2669193"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2602938"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.75"},{"key":"e_1_2_1_69_1","volume-title":"AAAI Conference on Artificial Intelligence. 3196--3202","author":"Zhao Qian"},{"key":"e_1_2_1_70_1","volume-title":"Vikas Singh, Grace Wahba, and Sterling C. Johnson.","author":"Zhou Hao","year":"2016"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3230709","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3230709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:57:29Z","timestamp":1750208249000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3230709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,29]]},"references-count":70,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018,11,30]]}},"alternative-id":["10.1145\/3230709"],"URL":"https:\/\/doi.org\/10.1145\/3230709","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,29]]},"assertion":[{"value":"2018-01-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-05-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-10-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}