{"type":"ScholarlyArticle","title":"Modal Consistency based Pre-Trained Multi-Model Reuse","authors":[{"name":"Yang Yang","slug":"yang-yang","given":"Yang","family":"Yang","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , Nanjing 210023 , China"},{"name":"De-Chuan Zhan","slug":"de-chuan-zhan","given":"De-Chuan","family":"Zhan","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , Nanjing 210023 , China"},{"name":"Xiang-Yu Guo","slug":"xiang-yu-guo","given":"Xiang-Yu","family":"Guo","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , Nanjing 210023 , China"},{"name":"Yuan Jiang","slug":"yuan-jiang","given":"Yuan","family":"Jiang","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , Nanjing 210023 , China"}],"abstract":"Multi-Model Reuse is one of the prominent problems in Learnware framework, while the main issue of Multi-Model Reuse lies in the final prediction acquisition from the responses of multiple pre-trained models. Different from multi-classifiers ensemble, there are only pre-trained models rather than the whole training sets provided in Multi-Model Reuse configuration. This configuration is closer to the real applications where the reliability of each model cannot be evaluated properly. In this paper, aiming at the lack of evaluation on reliability, the potential consistency spread on different modalities is utilized. With the consistency of pre-trained models on different modalities, we propose a Pre-trained Multi-Model Reuse approach PM2R with multi-modal data, which realizes the reusability of multiple models. PM2R can combine pre-trained multi-models efficiently without re-training, and consequently no more training data storage is required. We describe the more realistic Multi-Model Reuse setting comprehensively in our paper, and point out the differences among this setting, classifier ensemble and later fusion on multi-modal learning. Experiments on synthetic and real-world datasets validate the effectiveness of PM2R when it is compared with state-of-the-art ensemble/multi-modal learning methods under this more realistic setting.","doi":"10.24963/ijcai.2017/459","url":"https://ijcai.org/proceedings/2017/459","pdf":"https://ijcai.org/proceedings/2017/0459.pdf","markdown":"https://ijcai.org/proceedings/2017/459.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/459","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning S-Z","track":"Main track","number":459,"pages":{"first":3287,"last":3293},"keywords":["Machine Learning: Transfer, Adaptation, Multi-task Learning","Machine Learning: Multi-instance/Multi-label/Multi-view learning"],"videos":[],"references":[{"position":1,"raw":"[Blum and Mitchell, 1998] Avrim Blum and Tom Mitchell. Combining Labeled and Unlabeled Data with Co- Training. In Proceedings of the 11th Annual Conference on Computational Learning Theory, pages 92-100, Madi- son, WI, 1998.","title":"Combining Labeled and Unlabeled Data with Co-Training","authors":"Avrim Blum, Tom Mitchell","year":"1998","venue":"Proceedings of the 11th Annual Conference on Computational Learning Theory","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Breiman, 1996] Leo Breiman. Bagging predictors. Machine Learning, 24(2):123-140, 1996.","title":"Bagging predictors","authors":"Breiman","year":"1996","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Gao et al., 2008] Wen Gao, Bo Cao, Shiguang Shan, Xilin Chen, Delong Zhou, Xiaohua Zhang, and Debin Zhao. The CAS-PEAL Large-Scale Chinese Face Database and Base- line Evaluations. IEEE Transactions on System Man and Cybernetics, 38(1):149-161, 2008.","title":"The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations","authors":"Wen Gao, Bo Cao, Shiguang Shan, Xilin Chen, Delong Zhou, Xiaohua Zhang, Debin Zhao","year":"2008","venue":"IEEE Transactions on System Man and Cybernetics","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Isele et al., 2016] David Isele, Mohammad Rostami, and Eric Eaton. Using Task Features for Zero-Shot Knowledge Transfer in Lifelong Learning. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, pages 1620-1626, New York, NY, 2016.","title":"Using Task Features for Zero-Shot Knowledge Transfer in Lifelong Learning","authors":"David Isele, Mohammad Rostami, Eric Eaton","year":"2016","venue":"Proceedings of the 25th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2016/232"},{"position":5,"raw":"[Kandemir, 2015] Melih Kandemir. Asymmetric Transfer Learning with Deep Gaussian Processes. In Proceedings of the 32nd International Conference on Machine Learn- ing, pages 730-738, Lille, France, 2015.","title":"Asymmetric Transfer Learning with Deep Gaussian Processes","authors":"Melih Kandemir","year":"2015","venue":"Proceedings of the 32nd International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Khetan and Oh, 2016] Ashish Khetan and Sewoong Oh. Reliable Crowdsourcing under the Generalized Dawid- Skene Model. arXiv:1602.03481, 2016.","title":"Reliable Crowdsourcing under the Generalized Dawid-Skene Model","authors":"Ashish Khetan, Sewoong Oh","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Li et al., 2014] Shao-Yuan Li, Yuan Jiang, and Zhi-Hua Zhou. Partial Multi-View Clustering. In Proceedings of the 28th AAAI Conference on Artificial Intelligence, pages 1968-1974, Quebec City, Canada, 2014.","title":"Partial Multi-View Clustering","authors":"Shao-Yuan, Yuan Li, Zhi-Hua Jiang, Zhou","year":"2014","venue":"Proceedings of the 28th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Long and Wang, 2015] Mingsheng Long and Jianmin Wang. Learning Transferable Features with Deep Adapta- tion Networks. In Proceedings of the 32nd International Conference on Machine Learning, pages 97-105, Lille, France, 2015.","title":"Learning Transferable Features with Deep Adaptation Networks","authors":"Wang ; Long, Mingsheng Long, Jianmin Wang","year":"2015","venue":"Proceedings of the 32nd International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Pan and Yang, 2010] Sinno Jialin Pan and Qiang Yang. A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10):1345-1359, 2010.","title":"A Survey on Transfer Learning","authors":"Jialin Sinno, Qiang Pan, Yang","year":"2010","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Rothe et al., 2015] Rasmus Rothe, Radu Timofte, and Luc Van Gool. DEX: Deep EXpectation of Apparent Age from a Single Image. In Proceedings of the IEEE Interna- tional Conference on Computer Vision Workshops, pages 252-257, Santiago, Chile, 2015.","title":"DEX: Deep EXpectation of Apparent Age from a Single Image","authors":"Radu Rasmus Rothe, Luc Timofte, Van Gool","year":"2015","venue":"Proceedings of the IEEE International Conference on Computer Vision Workshops","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Schapire, 1990] Robert E. Schapire. The Strength of Weak Learnability. Machine Learning, 5(2):197-22, 1990.","title":"The Strength of Weak Learnability","authors":"Robert E Schapire","year":"1990","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Tan et al., 2017] Ben Tan, Yu Zhang, Sinno Jialin Pan, and Qiang Yang. Distant Domain Transfer Learning. In Pro- ceedings of the 31th AAAI Conference on Artificial Intelli- gence, San Francisco, CA, 2017.","title":"Distant Domain Transfer Learning","authors":"Ben Tan, Yu Zhang, Sinno Jialin Pan, Qiang Yang","year":"2017","venue":"Proceedings of the 31th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ueda, 2000] Naonori Ueda. Optimal Linear Combination of Neural Networks for Improving Classification Perfor- mance. IEEE Transactions on Pattern Analysis and Ma- chine Intelligence, 22(2):207-215, 2000.","title":"Optimal Linear Combination of Neural Networks for Improving Classification Performance","authors":"Naonori Ueda, Ueda","year":"2000","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Wang and Zhou, 2013] Wei Wang and Zhi-Hua Zhou. Co- training with Insufficient Views. In Proceedings of the 5th Asian Conference on Machine Learning, pages 467-482, Canberra, Australia, 2013.","title":"Cotraining with Insufficient Views","authors":"Wang, Zhou ; ] Wei, Wang, Zhi-Hua Zhou","year":"2013","venue":"Proceedings of the 5th Asian Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Wang et al., 2013] Hua Wang, Feiping Nie, and Heng Huang. Multi-View Clustering and Feature Learning via Structured Sparsity. In Proceedings of the 30th Interna- tional Conference on Machine Learning, pages 352-360, Atlanta, GA, 2013.","title":"Multi-View Clustering and Feature Learning via Structured Sparsity","authors":"Hua Wang, Feiping Nie, Heng Huang","year":"2013","venue":"Proceedings of the 30th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wang et al., 2016] Yang Wang, Wenjie Zhang, Lin Wu, Xuemin Lin, Meng Fang, and Shirui Pan. Iterative Views Agreement: An Iterative Low-Rank Based Structured Op- timization Method to Multi-View Spectral Clustering. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, pages 2153-2159, New York, NY, 2016.","title":"Iterative Views Agreement: An Iterative Low-Rank Based Structured Optimization Method to Multi-View Spectral Clustering","authors":"Yang Wang, Wenjie Zhang, Lin Wu, Xuemin Lin, Meng Fang, Shirui Pan","year":"2016","venue":"Proceedings of the 25th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2016/307"},{"position":17,"raw":"[Wei et al., 2016] Ying Wei, Yin Zhu, Cane Wing ki Leung, Yangqiu Song, and Qiang Yang. Instilling Social to Physi- cal: Co-Regularized Heterogeneous Transfer Learning. In Proceedings of the 30th AAAI Conference on Artificial In- telligence, pages 1338-1344, Phoenix, Arizona, 2016.","title":"Instilling Social to Physical: Co-Regularized Heterogeneous Transfer Learning","authors":"Ying Wei, Yin Zhu, Cane Wing Ki Leung, Yangqiu Song, Qiang Yang","year":"2016","venue":"Proceedings of the 30th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wolpert, 1992] David H. Wolpert. Stacked generalization. Neural Networks, 5(2):241-259, 1992.","title":"Stacked generalization","authors":"H David, Wolpert","year":"1992","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Xu et al., 2015] Chang Xu, Dacheng Tao, and Chao Xu. Multi-View Self-Paced Learning for Clustering. In Pro- ceedings of the 24th International Joint Conference on Ar- tificial Intelligence, pages 3974-3980, Buenos Aires, Ar- gentina, 2015.","title":"Multi-View Self-Paced Learning for Clustering","authors":"Chang Xu, Dacheng Tao, Chao Xu","year":"2015","venue":"Proceedings of the 24th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2015/558"},{"position":20,"raw":"[Yang et al., 2017] Yang Yang, De-Chuan Zhan, Ying Fan, Yuan Jiang, and Zhi-Hua Zhou. Deep Learning for Fixed Model Reuse. In Proceedings of the 31th AAAI Conference on Artificial Intelligence, pages 1751-1757, Phoenix, Ari- zona, 2017.","title":"Deep Learning for Fixed Model Reuse","authors":"Yang Yang, Ying De-Chuan Zhan, Yuan Fan, Zhi-Hua Jiang, Zhou","year":"2017","venue":"Proceedings of the 31th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ye et al., 2012] Guangnan Ye, Dong Liu, I-Hong Jhuo, and Shih-Fu Chang. Robust Late Fusion with Rank Mini- mization. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 3021-3028, Providence, RI, 2012.","title":"Robust Late Fusion with Rank Minimization","authors":"Guangnan Ye, Dong Liu, I-Hong Jhuo, Shih-Fu Chang","year":"2012","venue":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ye et al., 2015] Han-Jia Ye, De-Chuan Zhan, Yuan Miao, Yuan Jiang, and Zhi-Hua Zhou. Rank Consistency based Multi-View Learning: A Privacy-Preserving Approach. In Proceedings of the 24th ACM International Conference on Information and Knowledge Management, pages 991- 1000, Melbourne, Australia, 2015.","title":"Rank Consistency based Multi-View Learning: A Privacy-Preserving Approach","authors":"Han-Jia Ye, Yuan De-Chuan Zhan, Yuan Miao, Zhi-Hua Jiang, Zhou","year":"2015","venue":"Proceedings of the 24th ACM International Conference on Information and Knowledge Management","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yedidia et al., 2003] Jonathan S Yedidia, William T Free- man, and Yair Weiss. Understanding belief propagation and its generalizations. Exploring artificial intelligence in the new millennium, 8:236-239, 2003.","title":"Understanding belief propagation and its generalizations","authors":"Jonathan S Yedidia, William T Freeman, Yair Weiss","year":"2003","venue":"Exploring artificial intelligence in the new millennium","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhou et al., 2002] Zhi-Hua Zhou, Jianxin Wu, and Wei Tang. Ensembling neural networks: Many could be better than all. Artificial intelligence, 137(1-2):239-263, 2002.","title":"Ensembling neural networks: Many could be better than all","authors":"Zhi-Hua Zhou, Jianxin Wu, Wei Tang","year":"2002","venue":"Artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhou, 2016] Zhi-Hua Zhou. Learnware: On the Future of Machine Learning. Frontiers of Computer Science, 10(4):589-590, 2016.","title":"Learnware: On the Future of Machine Learning","authors":"Zhi-Hua Zhou","year":"2016","venue":"Frontiers of Computer Science","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}