Cited By
View all- Chen WCai ZLin PHuang YDu SGuo WWang S(2024)Multi-view semi-supervised classification via auto-weighted submarkov random walkExpert Systems with Applications10.1016/j.eswa.2024.124961256(124961)Online publication date: Dec-2024
Co-Training-Teaching: A Robust Semi-Supervised Framework for Review-Aware Rating Regression
Article No.: 41, Pages 1 - 16
Abstract
Review-aware Rating Regression (RaRR) suffers the severe challenge of extreme data sparsity as the multi-modality interactions of ratings accompanied by reviews are costly to obtain. Although some studies of semi-supervised rating regression are proposed to mitigate the impact of sparse data, they bear the risk of learning from noisy pseudo-labeled data. In this article, we propose a simple yet effective paradigm, called co-training-teaching (CoT2), for integrating the merits of both co-training and co-teaching toward robust semi-supervised RaRR. CoT2 employs two predictors trained with different feature sets of textual reviews, each of which functions as both “labeler” and “validator.” Specifically, one predictor (labeler) first labels unlabeled data for its peer predictor (validator); after that, the validator samples reliable instances from the noisy pseudo-labeled data it received and sends them back to the labeler for updating. By exchanging and validating pseudo-labeled instances, the two predictors are reinforced by each other in an iterative learning process. The final prediction is made by averaging the outputs of both the refined predictors. Extensive experiments show that our CoT2 considerably outperforms the state-of-the-art recommendation techniques in the RaRR task, especially when the training data is severely insufficient.
References
[1]
Devansh Arpit, Stanislaw Jastrzebski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S. Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, and Simon Lacoste-Julien. 2017. A closer look at memorization in deep networks. In Proceedings of ICML. 233–242.
[2]
David Berthelot, Nicholas Carlini, Ian J. Goodfellow, Nicolas Papernot, Avital Oliver, and Colin Raffel. 2019. MixMatch: A holistic approach to semi-supervised learning. In Proceedings of NeurIPS. 5050–5060.
[3]
David M. Blei, Andrew Y. Ng, and Michael I. Jordan. 2003. Latent Dirichlet allocation. Journal of Machine Learning Research 3 (2003), 993–1022.
[4]
Avrim Blum and Tom M. Mitchell. 1998. Combining labeled and unlabeled data with co-training. In Proceedings of COLT. 92–100.
[5]
Pengfei Chen, Benben Liao, Guangyong Chen, and Shengyu Zhang. 2019. Understanding and utilizing deep neural networks trained with noisy labels. In Proceedings of ICML, Vol. 97. 1062–1070.
[6]
Yair Dgani, Hayit Greenspan, and Jacob Goldberger. 2018. Training a neural network based on unreliable human annotation of medical images. In Proceedings of ISBI. 39–42.
[7]
Hao-Chen Dong, Yu-Feng Li, and Zhi-Hua Zhou. 2018. Learning from semi-supervised weak-label data. In Proceedings of AAAI. 2926–2933.
[8]
Xin Dong, Jingchao Ni, Wei Cheng, Zhengzhang Chen, Bo Zong, Dongjin Song, Yanchi Liu, Haifeng Chen, and Gerard de Melo. 2020. Asymmetrical hierarchical networks with attentive interactions for interpretable review-based recommendation. In Proceedings of AAAI. 7667–7674.
[9]
Jacob Goldberger and Ehud Ben-Reuven. 2017. Training deep neural-networks using a noise adaptation layer. In Proceedings of ICLR.
[10]
LanZhe Guo, Zhi Zhou, and YuFeng Li. 2022. Robust deep semi-supervised learning: A brief introduction. CoRR abs/2202.05975 (2022).
[11]
Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor W. Tsang, and Masashi Sugiyama. 2018. Co-teaching: Robust training of deep neural networks with extremely noisy labels. In Proceedings of NeurIPS. 8536–8546.
[12]
Yan Han, Soumava Kumar Roy, Lars Petersson, and Mehrtash Harandi. 2020. Learning from noisy labels via discrepant collaborative training. In Proceedings of WACV. IEEE, Los Alamitos, CA, 3158–3167.
[13]
Junheng Huang, Fangyuan Luo, and Jun Wu. 2021. Semi-supervised factorization machines for review-aware recommendation. In Proceedings of DASFAA, Vol. 12683. 85–99.
[14]
Lie Ju, Xin Wang, Lin Wang, Dwarikanath Mahapatra, Xin Zhao, Quan Zhou, Tongliang Liu, and Zongyuan Ge. 2022. Improving medical images classification with label noise using dual-uncertainty estimation. IEEE Transactions on Medical Imaging 41, 6 (2022), 1533–1546.
[15]
Davood Karimi, Haoran Dou, Simon K. Warfield, and Ali Gholipour. 2020. Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis. Medical Image Analysis 65 (2020), 101759.
[16]
Yoon Kim. 2014. Convolutional neural networks for sentence classification. In Proceedings of EMNLP. 1746–1751.
[17]
Yehuda Koren. 2008. Factorization meets the neighborhood: A multifaceted collaborative filtering model. In Proceedings of SIGKDD. 426–434.
[18]
Dong-Hyun Lee. 2013. Pseudo-Label: The simple and efficient semi-supervised learning method for deep neural networks. In Proceedings of ICML, Vol. 3. 896.
[19]
Junnan Li, Richard Socher, and Steven C. H. Hoi. 2020. DivideMix: Learning with noisy labels as semi-supervised learning. In Proceedings of ICLR.
[20]
Yu-Feng Li and Zhi-Hua Zhou. 2011. Towards making unlabeled data never hurt. In Proceedings of ICML. 1081–1088.
[21]
Donghua Liu, Jing Li, Bo Du, Jun Chang, and Rong Gao. 2019. DAML: Dual attention mutual learning between ratings and reviews for item recommendation. In Proceedings of SIGKDD. 344–352.
[22]
Songyin Luo, Xiangkui Lu, Jun Wu, and Jianbo Yuan. 2021. Review-aware neural recommendation with cross-modality mutual attention. In Proceedings of CIKM. ACM, New York, NY, 3293–3297.
[23]
Eran Malach and Shai Shalev-Shwartz. 2017. Decoupling “when to update” from “how to update.” In Proceedings of NeurIPS. 960–970.
[24]
Julian J. McAuley and Jure Leskovec. 2013. Hidden factors and hidden topics: Understanding rating dimensions with review text. In Proceedings of RecSys. 165–172.
[25]
Duc Tam Nguyen, Chaithanya Kumar Mummadi, Thi-Phuong-Nhung Ngo, Thi Hoai Phuong Nguyen, Laura Beggel, and Thomas Brox. 2020. SELF: Learning to filter noisy labels with self-ensembling. In Proceedings of ICLR.
[26]
Kento Nishi, Yi Ding, Alex Rich, and Tobias Hollerer. 2021. Augmentation strategies for learning with noisy labels. In Proceedings of CVPR. 8022–8031.
[27]
Giorgio Patrini, Alessandro Rozza, Aditya Krishna Menon, Richard Nock, and Lizhen Qu. 2017. Making deep neural networks robust to label noise: A loss correction approach. In Proceedings of CVPR. 2233–2241.
[28]
Yongli Ren, Gang Li, Jun Zhang, and Wanlei Zhou. 2012. The efficient imputation method for neighborhood-based collaborative filtering. In Proceedings of CIKM. 684–693.
[29]
Steffen Rendle. 2010. Factorization machines. In Proceedings of ICDM. 995–1000.
[30]
Mamshad Nayeem Rizve, Kevin Duarte, Yogesh Singh Rawat, and Mubarak Shah. 2021. In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning. In Proceedings of ICLR.
[31]
François Robinet, Claudia Parera, Christian Hundt, and Raphaël Frank. 2022. Weakly-supervised free space estimation through stochastic co-teaching. In Proceedings of WACV. 618–627.
[32]
Noveen Sachdeva and Julian J. McAuley. 2020. How useful are reviews for recommendation? A critical review and potential improvements. In Proceedings of SIGIR. 1845–1848.
[33]
Hwanjun Song, Minseok Kim, Dongmin Park, and Jae-Gil Lee. 2020. Learning from noisy labels with deep neural networks: A survey. CoRR abs/2007.08199 (2020).
[34]
Antti Tarvainen and Harri Valpola. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In Proceedings of NeurIPS. 1195–1204.
[35]
Jesper E. Van Engelen and Holger H. Hoos. 2020. A survey on semi-supervised learning. Machine Learning 109, 2 (2020), 373–440.
[36]
Wei Wang and Zhi-Hua Zhou. 2007. Analyzing co-training style algorithms. In Proceedings of ECML, Vol. 4701. 454–465.
[37]
Peter Welinder, Steve Branson, Serge J. Belongie, and Pietro Perona. 2010. The multidimensional wisdom of crowds. In Proceedings of NIPS. 2424–2432.
[38]
Jun Wu, Xiankai Sang, and Wei Cui. 2021. Semi-supervised collaborative filtering ensemble. World Wide Web 24, 2 (2021), 657–673.
[39]
Cheng Xue, Qi Dou, Xueying Shi, Hao Chen, and Pheng-Ann Heng. 2019. Robust learning at noisy labeled medical images: Applied to skin lesion classification. In Proceedings of ISBI. IEEE, Los Alamitos, CA, 1280–1283.
[40]
Yan Yan, Rómer Rosales, Glenn Fung, Subramanian Ramanathan, and Jennifer G. Dy. 2014. Learning from multiple annotators with varying expertise. Machine Learning 95, 3 (2014), 291–327.
[41]
Xiangli Yang, Zixing Song, Irwin King, and Zenglin Xu. 2021. A survey on deep semi-supervised learning. CoRR abs/2103.00550 (2021).
[42]
Yazhou Yao, Zeren Sun, Chuanyi Zhang, Fumin Shen, Qi Wu, Jian Zhang, and Zhenmin Tang. 2021. Jo-SRC: A contrastive approach for combating noisy labels. In Proceedings of CVPR. 5192–5201.
[43]
David Yarowsky. 1995. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of ACL. 189–196.
[44]
Xingrui Yu, Bo Han, Jiangchao Yao, Gang Niu, Ivor W. Tsang, and Masashi Sugiyama. 2019. How does disagreement help generalization against label corruption? In Proceedings of ICML, Vol. 97. 7164–7173.
[45]
Xiyu Yu, Tongliang Liu, Mingming Gong, and Dacheng Tao. 2018. Learning with biased complementary labels. In Proceedings of ECCV, Vol. 11205. 69–85.
[46]
Wang Zhan and Min-Ling Zhang. 2017. Inductive semi-supervised multi-label learning with co-training. In Proceedings of SIGKDD. ACM, New York, NY, 1305–1314.
[47]
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. 2017. Understanding deep learning requires rethinking generalization. In Proceedings of ICLR.
[48]
Hao Zhang, Liangxiao Jiang, and Wenqiang Xu. 2019. Multiple noisy label distribution propagation for crowdsourcing. In Proceedings of IJCAI. 1473–1479.
[49]
Jiyong Zhang and Pearl Pu. 2007. A recursive prediction algorithm for collaborative filtering recommender systems. In Proceedings of RecSys. 57–64.
[50]
Mi Zhang, Jie Tang, Xuchen Zhang, and Xiangyang Xue. 2014. Addressing cold start in recommender systems: A semi-supervised co-training algorithm. In Proceedings of SIGIR. 73–82.
[51]
Evgenii Zheltonozhskii, Chaim Baskin, Avi Mendelson, Alex M. Bronstein, and Or Litany. 2022. Contrast to divide: Self-supervised pre-training for learning with noisy labels. In Proceedings of WACV. 1657–1667.
[52]
ZhiHua Zhou. 2018. A brief introduction to weakly supervised learning. National Science Review 5, 1 (2018), 44–53.
[53]
ZhiHua Zhou and Ming Li. 2005. Semi-supervised regression with co-training. In Proceedings of IJCAI. 908–916.
[54]
ZhiHua Zhou and Ming Li. 2005. Tri-training: Exploiting unlabeled data using three classifiers. IEEE Transactions on Knowledge and Data Engineering 17, 11 (2005), 1529–1541.
[55]
ZhiHua Zhou and Ming Li. 2010. Semi-supervised learning by disagreement. Knowledge and Information Systems 24, 3 (2010), 415–439.
Index Terms
- Co-Training-Teaching: A Robust Semi-Supervised Framework for Review-Aware Rating Regression
Recommendations
Inductive Semi-supervised Multi-Label Learning with Co-Training
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningIn multi-label learning, each training example is associated with multiple class labels and the task is to learn a mapping from the feature space to the power set of label space. It is generally demanding and time-consuming to obtain labels for training ...
Stacked co-training for semi-supervised multi-label learning
AbstractDue to the difficulty of annotation, multi-label learning sometimes obtains a small amount of labeled data and a large amount of unlabeled data as supplements. To make up this issue, many algorithms extended the existing semi-supervised ...
Self-paced multi-label co-training
AbstractMulti-label learning aims to solve classification problems where instances are associated with a set of labels. In reality, it is generally easy to acquire unlabeled data but expensive or time-consuming to label them, and this ...
Comments
Information & Contributors
Information
Published In
February 2024
401 pages
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 13 November 2023
Online AM: 26 September 2023
Accepted: 06 September 2023
Revised: 23 March 2023
Received: 09 March 2022
Published in TKDD Volume 18, Issue 2
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Fundamental Research Funds for the Central Universities
- Open Research Fund from the Guangdong Provincial Key Laboratory of Big Data Computing, The Chinese University of Hong Kong, Shenzhen
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 252Total Downloads
- Downloads (Last 12 months)252
- Downloads (Last 6 weeks)8
Reflects downloads up to 12 Aug 2024
Other Metrics
Citations
Cited By
View all- Chen WCai ZLin PHuang YDu SGuo WWang S(2024)Multi-view semi-supervised classification via auto-weighted submarkov random walkExpert Systems with Applications10.1016/j.eswa.2024.124961256(124961)Online publication date: Dec-2024
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in