short-paper

CIFDM: Continual and Interactive Feature Distillation for Multi-Label Stream Learning

Authors:

Dingcheng LiAuthors Info & Claims

SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

Pages 2121 - 2125

https://doi.org/10.1145/3404835.3463096

Published: 11 July 2021 Publication History

Abstract

Multi-label learning algorithms have attracted more and more attention as of recent. This is mainly because real-world data is generally associated with multiple and non-exclusive labels, which could correspond to different objects, scenes, actions, and attributes. In this paper, we consider the following challenging multi-label stream scenario: the new labels emerge continuously in the changing environments, and are assigned to the previous data. In this setting, data mining solutions must be able to learn the new concepts and avoid catastrophic forgetting simultaneously. We propose a novel continual and interactive feature distillation-based learning framework (CIFDM), to effectively classify instances with novel labels. We utilize the knowledge from the previous tasks to learn new knowledge to solve the current task. Then, the system compresses historical and novel knowledge and preserves it while waiting for new emerging tasks. CIFDM consists of three components: 1) a knowledge bank that stores the existing feature-level compressed knowledge, and predicts the observed labels so far; 2) a pioneer module that aims to learn and predict new emerged labels based on knowledge bank.; 3) an interactive knowledge compression function which is used to compress and transfer the new knowledge to the bank, and then apply the current compressed knowledge to initialize the label embedding of the pioneer for the next task.

Supplementary Material

MP4 File (SIGIR21-sp1680.mp4)

The video for the paper "CIFDM: Continual and Interactive Feature Distillation for Multi-Label Stream Learning".

Download
7.86 MB

References

[1]

Rahaf Aljundi, Francesca Babiloni, Mohamed Elhoseiny, Marcus Rohrbach, and Tinne Tuytelaars. 2018. Memory aware synapses: Learning what (not) to forget. In ECCV. 139--154.

[2]

Jimmy Ba and Rich Caruana. 2014. Do deep nets really need to be deep?. In Advances in neural information processing systems. 2654--2662.

[3]

Emanuel Ben-Baruch, Tal Ridnik, Nadav Zamir, Asaf Noy, Itamar Friedman, Matan Protter, and Lihi Zelnik-Manor. 2020. Asymmetric Loss For Multi-Label Classification. arXiv preprint arXiv:2009.14119 (2020).

[4]

Kush Bhatia, Himanshu Jain, Purushottam Kar, Manik Varma, and Prateek Jain. 2015. Sparse local embeddings for extreme multi-label classification. In Advances in neural information processing systems. 730--738.

[5]

André Elisseeff, Jason Weston, et al. 2001. A kernel method for multi-labelled classification. In NIPS, Vol. 14. 681--687.

Digital Library

[6]

Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik. 2014a. Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR. 580--587.

[7]

Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik. 2014b. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 580--587.

Digital Library

[8]

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.

[9]

Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015).

[10]

Mark J Huiskes and Michael S Lew. 2008. The mir flickr retrieval evaluation. In Proceedings of the 1st ACM international conference on Multimedia information retrieval. 39--43.

Digital Library

[11]

Eun-Sol Kim, Kyoung-Woon On, Jongseok Kim, Yu-Jung Heo, Seong-Ho Choi, Hyun-Dong Lee, and Byoung-Tak Zhang. 2018. Temporal attention mechanism with conditional inference for large-scale multi-label video classification. In ECCV Workshops. 0--0.

[12]

James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al. 2017. Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences (2017), 201611835.

[13]

Zhizhong Li and Derek Hoiem. 2017. Learning without forgetting. IEEE transactions on pattern analysis and machine intelligence, Vol. 40, 12 (2017), 2935--2947.

[14]

Weiwei Liu and Xiaobo Shen. 2019. Sparse Extreme Multi-label Learning with Oracle Property. In International Conference on Machine Learning. 4032--4041.

[15]

Mohammad Masud, Jing Gao, Latifur Khan, Jiawei Han, and Bhavani M Thuraisingham. 2010. Classification and novel class detection in concept-drifting data streams under time constraints. IEEE Transactions on Knowledge and Data Engineering, Vol. 23, 6 (2010), 859--874.

Digital Library

[16]

Jinseok Nam, Jungi Kim, Eneldo Loza Menc'ia, Iryna Gurevych, and Johannes Fürnkranz. 2014. Large-scale multi-label text classification-revisiting neural networks. In Joint european conference on machine learning and knowledge discovery in databases. Springer, 437--452.

[17]

Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H Lampert. 2017. icarl: Incremental classifier and representation learning. In CVPR. 2001--2010.

[18]

Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. 2017. Continual learning with deep generative replay. In NIPS. 2990--2999.

Digital Library

[19]

Zhuoyi Wang, Bo Dong, Yu Lin, Yigong Wang, Md Shihabul Islam, and Latifur Khan. 2019. Co-representation learning framework for the open-set data classification. In 2019 IEEE International Conference on Big Data (Big Data). 239--244.

[20]

Zhen Wang, Liu Liu, and Dacheng Tao. 2020 a. Deep Streaming Label Learning. In International Conference on Machine Learning (ICML). 378--387.

[21]

Zhuoyi Wang, Yigong Wang, Yu Lin, Evan Delord, and Khan Latifur. 2020 b. Few-sample and adversarial representation learning for continual stream mining. In WWW. 718--728.

[22]

Kun Wei, Cheng Deng, Xu Yang, and Maosen Li. 2021. Incremental Embedding Learning via Zero-Shot Translation. AAAI (2021).

[23]

Chih-Kuan Yeh, Wei-Chieh Wu, Wei-Jen Ko, and Yu-Chiang Frank Wang. 2017. Learning deep latent space for multi-label classification. In AAAI, Vol. 31.

[24]

Friedemann Zenke, Ben Poole, and Surya Ganguli. 2017. Continual learning through synaptic intelligence. In ICML. 3987--3995.

[25]

Min-Ling Zhang and Zhi-Hua Zhou. 2006. Multilabel neural networks with applications to functional genomics and text categorization. IEEE transactions on Knowledge and Data Engineering, Vol. 18, 10 (2006), 1338--1351.

Digital Library

Cited By

Gaudreault JBranco P(2024)A Systematic Literature Review of Novelty Detection in Data Streams: Challenges and OpportunitiesACM Computing Surveys10.1145/365728656:10(1-37)Online publication date: 12-Apr-2024
https://dl.acm.org/doi/10.1145/3657286
Awal Kassim MViktor HMichalowski W(2024)Multi-Label Lifelong Machine Learning: A Scoping Review of Algorithms, Techniques, and ApplicationsIEEE Access10.1109/ACCESS.2024.340356912(74539-74557)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3403569
Wen HZhang XSong XWei YNie LEl Saddik AMei TCucchiara RBertini MTobon Vallejo DAtrey PHossain M(2023)Target-Guided Composed Image RetrievalProceedings of the 31st ACM International Conference on Multimedia10.1145/3581783.3611817(915-923)Online publication date: 26-Oct-2023
https://dl.acm.org/doi/10.1145/3581783.3611817
Show More Cited By

Index Terms

CIFDM: Continual and Interactive Feature Distillation for Multi-Label Stream Learning
1. Computing methodologies
  1. Machine learning
2. Information systems
  1. Information systems applications

Recommendations

Instance Annotation for Multi-Instance Multi-Label Learning
Special Issue on ACM SIGKDD 2012

Multi-instance multi-label learning (MIML) is a framework for supervised classification where the objects to be classified are bags of instances associated with multiple labels. For example, an image can be represented as a bag of segments and ...
Multi-label double-layer learning for cross-modal retrieval

This paper proposes a novel method named Multi-label Double-layer Learning (MDLL) for multi-label cross-modal retrieval task. MDLL includes two stages (layers): L2C (Label to Common) and C2L (Common to Label). In the L2C stage, considering that labels ...
Dynamic Label Propagation for Semi-supervised Multi-class Multi-label Classification
ICCV '13: Proceedings of the 2013 IEEE International Conference on Computer Vision

In graph-based semi-supervised learning approaches, the classification rate is highly dependent on the size of the availabel labeled data, as well as the accuracy of the similarity measures. Here, we propose a semi-supervised multi-class/multi-label ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

July 2021

2998 pages

ISBN:9781450380379

DOI:10.1145/3404835

General Chairs:
Fernando Diaz
(Google)
,
Chirag Shah
University of Washington
,
Torsten Suel
New York University
,
Program Chairs:
Pablo Castells
Universidad Autónoma de Madrid, Amazon
,
Rosie Jones
Spotify
,
Tetsuya Sakai
Waseda University

Copyright © 2021 ACM.

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

SIGIR: ACM Special Interest Group on Information Retrieval

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 11 July 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper

Conference

SIGIR '21

Sponsor:

SIGIR

SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

July 11 - 15, 2021

Virtual Event, Canada

Acceptance Rates

Overall Acceptance Rate 792 of 3,983 submissions, 20%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

8
Total Citations
View Citations
272
Total Downloads

Downloads (Last 12 months)57
Downloads (Last 6 weeks)4

Reflects downloads up to 30 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

Gaudreault JBranco P(2024)A Systematic Literature Review of Novelty Detection in Data Streams: Challenges and OpportunitiesACM Computing Surveys10.1145/365728656:10(1-37)Online publication date: 12-Apr-2024
https://dl.acm.org/doi/10.1145/3657286
Awal Kassim MViktor HMichalowski W(2024)Multi-Label Lifelong Machine Learning: A Scoping Review of Algorithms, Techniques, and ApplicationsIEEE Access10.1109/ACCESS.2024.340356912(74539-74557)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3403569
Wen HZhang XSong XWei YNie LEl Saddik AMei TCucchiara RBertini MTobon Vallejo DAtrey PHossain M(2023)Target-Guided Composed Image RetrievalProceedings of the 31st ACM International Conference on Multimedia10.1145/3581783.3611817(915-923)Online publication date: 26-Oct-2023
https://dl.acm.org/doi/10.1145/3581783.3611817
Zhang DTaneva-Popova BYoshioka MKiseleva JAliannejadi M(2023)A Theoretical Analysis of Out-of-Distribution Detection in Multi-Label ClassificationProceedings of the 2023 ACM SIGIR International Conference on Theory of Information Retrieval10.1145/3578337.3605116(275-282)Online publication date: 9-Aug-2023
https://dl.acm.org/doi/10.1145/3578337.3605116
Li DYang PZhang YLi PChen HDuh WHuang HKato MMothe JPoblete B(2023)Power Norm Based Lifelong Learning for Paraphrase GenerationsProceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3539618.3592039(2266-2271)Online publication date: 19-Jul-2023
https://dl.acm.org/doi/10.1145/3539618.3592039
Mishra SSundaram S(2023)A Memory-Free Evolving Bipolar Neural Network for Efficient Multi-Label Stream LearningICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)10.1109/ICASSP49357.2023.10095002(1-5)Online publication date: 4-Jun-2023
https://doi.org/10.1109/ICASSP49357.2023.10095002
Costa JFaria ESilva JGama JCerri R(2023)Novelty detection for multi-label stream classification under extreme verification latencyApplied Soft Computing10.1016/j.asoc.2023.110265141:COnline publication date: 1-Jul-2023
https://dl.acm.org/doi/10.1016/j.asoc.2023.110265
Wang ZLi DLi PAl Hasan MXiong L(2022)Latent Coreset Sampling based Data-Free Continual LearningProceedings of the 31st ACM International Conference on Information & Knowledge Management10.1145/3511808.3557375(2077-2087)Online publication date: 17-Oct-2022
https://dl.acm.org/doi/10.1145/3511808.3557375

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.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents