skip to main content
10.1145/3583780.3615149acmconferencesArticle/Chapter ViewAbstractPublication PagescikmConference Proceedingsconference-collections
short-paper

Target-oriented Few-shot Transferring via Measuring Task Similarity

Published: 21 October 2023 Publication History

Abstract

Despite significant progress in recent years, few-shot learning (FSL) still faces two critical challenges. Firstly, most FSL solutions in the training phase rely on exploiting auxiliary tasks, while target tasks are underutilized. Secondly, current benchmarks sample numerous target tasks, each with only an N-way C-shot shot query set in the evaluation phase, which is not representative of real-world scenarios. To address these issues, we propose Guidepost, a target-oriented FSL method that can implicitly learn task similarities using a task-level learn-to-learn mechanism and then re-weight auxiliary tasks. Additionally, we introduce a new FSL benchmark that satisfies realistic needs and aligns with our target-oriented approach. Mainstream FSL methods struggle under this new experimental setting. Extensive experiments demonstrate that Guidepost outperforms two classical few-shot learners, i.e., MAML and ProtoNet, and one state-of-the-art few-shot learner, i.e., RENet, on several FSL image datasets. Furthermore, we implement Guidepost as a domain adaptor to achieve high accuracy wireless sensing on our collected WiFi-based human activity recognition dataset.

References

[1]
Shuhao Cui, Xuan Jin, et al. 2020. Heuristic domain adaptation. Advances in Neural Information Processing Systems, Vol. 33 (2020), 7571--7583.
[2]
Shuya Ding, Zhe Chen, Tianyue Zheng, and Jun Luo. 2020. RF-net: A unified meta-learning framework for RF-enabled one-shot human activity recognition. In Proceedings of the 18th Conference on Embedded Networked Sensor Systems. 517--530.
[3]
Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning. PMLR, 1126--1135.
[4]
Taesik Gong, Yeonsu Kim, et al. 2019. Metasense: few-shot adaptation to untrained conditions in deep mobile sensing. In Proceedings of the 17th Conference on Embedded Networked Sensor Systems. 110--123.
[5]
Wei Gong, Si Chen, and Jiangchuan Liu. 2017a. Towards higher throughput rate adaptation for backscatter networks. In 2017 IEEE 25th International Conference on Network Protocols (ICNP). IEEE, 1--10.
[6]
Wei Gong, Jiangchuan Liu, and Zhe Yang. 2016. Fast and reliable unknown tag detection in large-scale RFID systems. In Proceedings of the 17th ACM International Symposium on Mobile Ad Hoc Networking and Computing. 141--150.
[7]
Wei Gong, Jiangchuan Liu, and Zhe Yang. 2017b. Efficient unknown tag detection in large-scale RFID systems with unreliable channels. IEEE/ACM Transactions on Networking, Vol. 25, 4 (2017), 2528--2539.
[8]
Wei Gong, Ivan Stojmenovic, Amiya Nayak, Kebin Liu, and Haoxiang Liu. 2015. Fast and scalable counterfeits estimation for large-scale RFID systems. IEEE/ACM transactions on networking, Vol. 24, 2 (2015), 1052--1064.
[9]
Wenjun Jiang et al. 2018. Towards environment independent device free human activity recognition. In Proceedings of the 24th annual international conference on mobile computing and networking. 289--304.
[10]
Dahyun Kang, Heeseung Kwon, et al. 2021. Relational embedding for few-shot classification. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 8822--8833.
[11]
Kai Li, Chang Liu, Handong Zhao, Yulun Zhang, and Yun Fu. 2020. Semi-supervised domain adaptation with prototypical alignment and consistency learning. (2020).
[12]
Haoxiang Liu, Wei Gong, Lei Chen, Wenbo He, Kebin Liu, and Yunhao Liu. 2014a. Generic composite counting in RFID systems. In 2014 IEEE 34th International Conference on Distributed Computing Systems. IEEE, 597--606.
[13]
Kebin Liu, Qiang Ma, Wei Gong, Xin Miao, and Yunhao Liu. 2014b. Self-diagnosis for detecting system failures in large-scale wireless sensor networks. IEEE Transactions on Wireless Communications, Vol. 13, 10 (2014), 5535--5545.
[14]
Zhenguo Shi et al. 2020. Environment-robust device-free human activity recognition with channel-state-information enhancement and one-shot learning. IEEE Transactions on Mobile Computing (2020).
[15]
Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems, Vol. 30 (2017).
[16]
Qiuling Suo, Jingyuan Chou, et al. 2020. Tadanet: Task-adaptive network for graph-enriched meta-learning. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1789--1799.
[17]
Qiwei Wang, Si Chen, Jia Zhao, and Wei Gong. 2021. Rapidrider: Efficient wifi backscatter with uncontrolled ambient signals. In IEEE INFOCOM 2021-IEEE Conference on Computer Communications. IEEE, 1--10.
[18]
Huaxiu Yao, Yu Wang, Ying Wei, Peilin Zhao, Mehrdad Mahdavi, Defu Lian, and Chelsea Finn. 2021. Meta-learning with an adaptive task scheduler. Advances in Neural Information Processing Systems, Vol. 34 (2021), 7497--7509.
[19]
Jihong Yu, Jiangchuan Liu, Rongrong Zhang, Lin Chen, Wei Gong, and Shurong Zhang. 2019. Multi-seed group labeling in RFID systems. IEEE transactions on mobile computing, Vol. 19, 12 (2019), 2850--2862.
[20]
Mingyue Yuan, Dong Yin, Jinwen Ding, Zhipeng Zhou, Chengfeng Zhu, Rui Zhang, and An Wang. 2019. A multi-image Joint Re-ranking framework with updateable Image Pool for person re-identification. Journal of Visual Communication and Image Representation, Vol. 59 (2019), 527--536.
[21]
Maolin Zhang, Si Chen, Jia Zhao, and Wei Gong. 2021. Commodity-level BLE backscatter. In Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services. 402--414.
[22]
Maolin Zhang, Jia Zhao, Si Chen, and Wei Gong. 2020. Reliable backscatter with commodity ble. In IEEE INFOCOM 2020-IEEE Conference on Computer Communications. IEEE, 1291--1299.
[23]
Jia Zhao, Wei Gong, and Jiangchuan Liu. 2020. Towards scalable backscatter sensor mesh with decodable relay and distributed excitation. In Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services. 67--79.
[24]
Zhipeng Zhou, Lanqing Li, Peilin Zhao, Pheng-Ann Heng, and Wei Gong. 2023. Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3499--3509.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
October 2023
5508 pages
ISBN:9798400701245
DOI:10.1145/3583780
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].

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 21 October 2023

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. few-shot learning
  2. learn to learn
  3. task similarity

Qualifiers

  • Short-paper

Funding Sources

Conference

CIKM '23
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

  • 0
    Total Citations
  • 108
    Total Downloads
  • Downloads (Last 12 months)62
  • Downloads (Last 6 weeks)2
Reflects downloads up to 01 Jan 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media