skip to main content
10.1145/3459637.3482251acmconferencesArticle/Chapter ViewAbstractPublication PagescikmConference Proceedingsconference-collections
research-article

Detecting the Fake Candidate Instances: Ambiguous Label Learning with Generative Adversarial Networks

Published: 30 October 2021 Publication History

Abstract

Ambiguous Label Learning (ALL), as an emerging paradigm of weakly supervised learning, aims to induce the prediction model from training datasets with ambiguous supervision, where, specifically, each training instance is annotated with a set of candidate labels but only one is valid. To handle this task, the existing shallow methods mainly disambiguate the candidate labels by leveraging various regularization techniques. Inspired by the great success of deep generative adversarial networks, we apply it to perform effective candidate label disambiguation from a new instance-pivoted perspective. Specifically, for each ALL instance, we recombine its feature representation with each of candidate labels to generate a set of candidate instances, where only one is real and all others are fake. We formulate a unified adversarial objective with respect to three players, i.e., a discriminator, a generator, and a classifier. The discriminator is used to detect the fake candidate instances, so that the classifier can be trained without them. With this insight, we develop a novel ALL method, namely Adversarial Ambiguous Label Learning with Candidate Instance Detection (A2L2CID). Theoretically, we analyze that there is a global equilibrium point between the three players. Empirically, extensive experimental results indicate that A2L2CID outperforms the state-of-the-art ALL methods.

References

[1]
Jessa Bekker and Jesse Davis. 2020. Learning from Positive and Unlabeled Data: A Survey. Machine Learning, Vol. 109, 4 (2020), 719--760.
[2]
Forrest Briggs, Xiaoli Z. Fern, and Raviv Raich. 2012. Rank-Loss Support Instance Machines for MIML Instance Annotation. In ACM SIGKDD. 534--542.
[3]
Brian Chen, Bo Wu, Alireza Zareian, Hanwang Zhang, and Shih-Fu Chang. 2020. General Partial Label Learning via Dual Bipartite Graph Autoencoder. In AAAI. 10502--10509.
[4]
Ching-Hui Chen, Vishal M. Patel, and Rama Chellappa. 2018. Learning from Ambiguously Labeled Face Images. IEEE TPAMI, Vol. 40, 7 (2018), 1653--1667.
[5]
Yi-Chen Chen, Vishal M. Patel, Rama Chellappa, and P. Jonathon Phillips. 2014. Ambiguously Labeled Learning using Dictionaries. IEEE TIFS, Vol. 9, 12 (2014), 2076--2088.
[6]
Yunjey Choi, Min-Je Choi, Munyoung Kim, Jung-Woo Ha, Sunghun Kim, and Jaegul Choo. 2018. StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation. In IEEE CVPR. 8789--8797.
[7]
Yunjey Choi, Youngjung Uh, Jaejun Yoo, and Jung-Woo Ha. 2020. StarGAN v2: Diverse Image Synthesis for Multiple Domains. In IEEE CVPR. 8185--8194.
[8]
Timothée Cour, Benjamin Sapp, Chris Jordan, and Ben Taskar. 2009. Learning from Ambiguously Labeled Images. In IEEE CVPR. 919--926.
[9]
Timothé e Cour, Benjamin Sapp, and Ben Taskar. 2011. Learning from Partial Labels. JMLR, Vol. 12, 5 (2011), 1501--1536.
[10]
Lei Feng and Bo An. 2018. Leveraging Latent Label Distributions for Partial Label Learning. In IJCAI. 2107--2113.
[11]
Lei Feng and Bo An. 2019a. Partial Label Learning by Semantic Difference Maximization. In IJCAI. 2294--2300.
[12]
Lei Feng and Bo An. 2019b. Partial Label Learning with Self-Guided Retraining. In AAAI. 3542--3549.
[13]
Lei Feng, Takuo Kaneko, Bo Han, Gang Niu, Bo An, and Masashi Sugiyama. 2020a. Learning from Multiple Complementary Labels. In ICML. 3072--3081.
[14]
Lei Feng, Jiaqi Lv, Bo Han, Miao Xu, Gang Niu, Xin Geng, Bo An, and Masashi Sugiyama. 2020b. Provably Consistent Partial-Label Learning. In NeurIPS.
[15]
Chen Gong, Tongliang Liu, Yuanyan Tang, Jian Yang, Jie Yang, and Dacheng Tao. 2018. A Regularization Approach for Instance-Based Superset Label Learning. IEEE Transactions on Cybernetics, Vol. 48, 3 (2018), 967--978.
[16]
Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In NeurIPS. 2672--2680.
[17]
Matthieu Guillaumin, Jakob J. Verbeek, and Cordelia Schmid. 2010. Multiple Instance Metric Learning from Automatically Labeled Bags of Faces. In ECCV. 634--647.
[18]
Sheng-Jun Huang, Wei Gao, and Zhi-Hua Zhou. 2019. Fast Multi-Instance Multi-Label Learning. IEEE TPAMI, Vol. 41, 11 (2019), 2614--2627.
[19]
Eyke Hü llermeier and Jü rgen Beringer. 2006. Learning from Ambiguously Labeled Examples. Intelligent Data Analysis, Vol. 10, 5 (2006), 419--439.
[20]
Eyke Hü llermeier and Weiwei Cheng. 2015. Superset Learning Based on Generalized Loss Minimization. In ECML PKDD. 260--275.
[21]
Takashi Ishida, Gang Niu, Aditya Krishna Menon, and Masashi Sugiyama. 2019. Complementary-Label Learning for Arbitrary Losses and Models. In ICML. 2971--2980.
[22]
Rong Jin and Zoubin Ghahramani. 2002. Learning with Multiple Labels. In NeurIPS. 897--904.
[23]
Diederik P Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980 (2014).
[24]
Changchun Li, Ximing Li, and Jihong Ouyang. 2020a. Learning with Noisy Partial Labels by Simultaneously Leveraging Global and Local Consistencies. In ACM CIKM. 725--734.
[25]
Changchun Li, Ximing Li, and Jihong Ouyang. 2021. Semi-Supervised Text Classification with Balanced Deep Representation Distributions. In ACL. 5044--5053.
[26]
Chongxuan Li, Kun Xu, Jiashuo Liu, Jun Zhu, and Bo Zhang. 2019. Triple Generative Adversarial Networks. arXiv preprint arXiv:1912.09784 (2019).
[27]
Chongxuan Li, Taufik Xu, Jun Zhu, and Bo Zhang. 2017. Triple Generative Adversarial Nets. In NeurIPS. 4088--4098.
[28]
Junnan Li, Richard Socher, and Steven C. H. Hoi. 2020b. DivideMix: Learning with Noisy Labels as Semi-supervised Learning. In ICLR.
[29]
Li-Ping Liu and Thomas G. Dietterich. 2012. A Conditional Multinomial Mixture Model for Superset Label Learning. In NeurIPS. 557--565.
[30]
Jie Luo and Francesco Orabona. 2010. Learning from Candidate Labeling Sets. In NeurIPS. 1504--1512.
[31]
Jiaqi Lv, Miao Xu, Lei Feng, Gang Niu, Xin Geng, and Masashi Sugiyama. 2020. Progressive Identification of True Labels for Partial-Label Learning. In ICML. 6500--6510.
[32]
Mehdi Mirza and Simon Osindero. 2014. Conditional Generative Adversarial Nets. arXiv preprint arXiv:1411.1784 (2014).
[33]
Takeru Miyato and Masanori Koyama. 2018. CGANs with Projection Discriminator. In ICLR.
[34]
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 ICLR.
[35]
Nam Nguyen and Rich Caruana. 2008. Classification with Partial Labels. In ACM SIGKDD. 551--559.
[36]
Gabriel Panis and Andreas Lanitis. 2014. An Overview of Research Activities in Facial Age Estimation Using the FG-NET Aging Database. In ECCV. 737--750.
[37]
Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In NeurIPS. 8024--8035.
[38]
Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vander Plas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, and Edouard Duchesnay. 2011. Scikit-learn: Machine Learning in Python. JMLR, Vol. 12 (2011), 2825--2830.
[39]
Tim Salimans, Ian J. Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved Techniques for Training GANs. In NeurIPS. 2226--2234.
[40]
Jiaming Song, Hongyu Ren, Dorsa Sadigh, and Stefano Ermon. 2018. Multi-Agent Generative Adversarial Imitation Learning. In NeurIPS. 7472--7483.
[41]
Jost Tobias Springenberg. 2016. Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks. In ICLR.
[42]
Cai-Zhi Tang and Min-Ling Zhang. 2017. Confidence-Rated Discriminative Partial Label Learning. In AAAI. 2611--2617.
[43]
Jesper E. van Engelen and Holger H. Hoos. 2020. A Survey on Semi-Supervised Learning. Machine Learning, Vol. 109, 2 (2020), 373--440.
[44]
Si Wu, Guangchang Deng, Jichang Li, Rui Li, Zhiwen Yu, and Hau-San Wong. 2019. Enhancing TripleGAN for Semi-Supervised Conditional Instance Synthesis and Classification. In IEEE CVPR. 10091--10100.
[45]
Xuan Wu and Min-Ling Zhang. 2018. Towards Enabling Binary Decomposition for Partial Label Learning. In IJCAI. 2868--2874.
[46]
Yuying Xing, Guoxian Yu, Jun Wang, Carlotta Domeniconi, and Xiangliang Zhang. 2020. Weakly-Supervised Multi-View Multi-Instance Multi-Label Learning. In IJCAI. 3124--3130.
[47]
Ning Xu, Jiaqi Lv, and Xin Geng. 2019a. Partial Label Learning via Label Enhancement. In AAAI. 5557--5564.
[48]
Yixing Xu, Yunhe Wang, Hanting Chen, Kai Han, Chunjing Xu, Dacheng Tao, and Chang Xu. 2019b. Positive-Unlabeled Compression on the Cloud. In NeurIPS. 2561--2570.
[49]
Yao Yao, Chen Gong, Jiehui Deng, and Jian Yang. 2020. Network Cooperation with Progressive Disambiguation for Partial Label Learning. arXiv preprint arXiv:2002.11919 (2020).
[50]
Fei Yu and Min-Ling Zhang. 2015. Maximum Margin Partial Label Learning. In ACML. 96--111.
[51]
Fei Yu and Min-Ling Zhang. 2017. Maximum Margin Partial Label Learning. Machine Learning, Vol. 106, 4 (2017), 573--593.
[52]
Zinan Zeng, Shijie Xiao, Kui Jia, Tsung-Han Chan, Shenghua Gao, Dong Xu, and Yi Ma. 2013. Learning by Associating Ambiguously Labeled Images. In IEEE CVPR. 708--715.
[53]
Min-Ling Zhang and Fei Yu. 2015. Solving the Partial Label Learning Problem: An Instance-Based Approach. In IJCAI. 4048--4054.
[54]
Min-Ling Zhang, Fei Yu, and Cai-Zhi Tang. 2017. Disambiguation-Free Partial Label Learning. IEEE TKDE, Vol. 29, 10 (2017), 2155--2167.
[55]
Min-Ling Zhang, Bin-Bin Zhou, and Xu-Ying Liu. 2016. Partial Label Learning via Feature-Aware Disambiguation. In ACM SIGKDD. 1335--1344.
[56]
Min-Ling Zhang, Bin-Bin Zhou, and Xu-Ying Liu. 2019b. Adaptive Graph Guided Disambiguation for Partial Label Learning. In ACM SIGKDD. 83--91.
[57]
Xiaofeng Zhang, Zhangyang Wang, Dong Liu, and Qing Ling. 2019a. DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification. In IEEE ICASSP. 2807--2811.
[58]
Yabin Zhang, Guang Yang, Suyun Zhao, Peng Ni, Hairong Lian, Hong Chen, and Cuiping Li. 2020. Partial Label Learning via Generative Adversarial Nets. In ECAI. 1674--1681.
[59]
Zhengli Zhao, Sameer Singh, Honglak Lee, Zizhao Zhang, Augustus Odena, and Han Zhang. 2020. Improved Consistency Regularization for GANs. arXiv preprint arXiv:2002.04724 (2020).
[60]
Zhi-Hua Zhou. 2018. A Brief Introduction to Weakly Supervised Learning. National Science Review, Vol. 5, 1 (2018), 44--53.
[61]
Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros. 2017. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In IEEE ICCV. 2242--2251.

Cited By

View all
  • (2025)Addressing bayes imbalance in partial label learning via range adaptive graph guided disambiguationNeurocomputing10.1016/j.neucom.2025.129606627(129606)Online publication date: Apr-2025
  • (2024)Confidence-Induced Granular Partial Label Feature Selection via Dependency and SimilarityIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2024.340548936:11(5797-5810)Online publication date: Nov-2024
  • (2024)Partial label feature selection based on noisy manifold and label distributionPattern Recognition10.1016/j.patcog.2024.110791156(110791)Online publication date: Dec-2024
  • Show More Cited By

Index Terms

  1. Detecting the Fake Candidate Instances: Ambiguous Label Learning with Generative Adversarial Networks

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Conferences
      CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management
      October 2021
      4966 pages
      ISBN:9781450384469
      DOI:10.1145/3459637
      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 ACM 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]

      Sponsors

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 30 October 2021

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. ambiguous label learning
      2. candidate instance
      3. triple-gan

      Qualifiers

      • Research-article

      Funding Sources

      • National Natural Science Foundation of China (NSFC)
      • Key R&D Projects of Science and Technology Department of Jilin Province of China

      Conference

      CIKM '21
      Sponsor:

      Acceptance Rates

      Overall Acceptance Rate 1,861 of 8,427 submissions, 22%

      Upcoming Conference

      CIKM '25

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)35
      • Downloads (Last 6 weeks)2
      Reflects downloads up to 28 Feb 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2025)Addressing bayes imbalance in partial label learning via range adaptive graph guided disambiguationNeurocomputing10.1016/j.neucom.2025.129606627(129606)Online publication date: Apr-2025
      • (2024)Confidence-Induced Granular Partial Label Feature Selection via Dependency and SimilarityIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2024.340548936:11(5797-5810)Online publication date: Nov-2024
      • (2024)Partial label feature selection based on noisy manifold and label distributionPattern Recognition10.1016/j.patcog.2024.110791156(110791)Online publication date: Dec-2024
      • (2022)SoLarProceedings of the 36th International Conference on Neural Information Processing Systems10.5555/3600270.3600858(8104-8117)Online publication date: 28-Nov-2022
      • (2022)Learning with partial multi-labeled data by leveraging low-rank constraint and decompositionApplied Intelligence10.1007/s10489-022-03989-053:7(8133-8145)Online publication date: 28-Jul-2022

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media