Gradient Coordination for Quantifying and Maximizing Knowledge Transference in Multi-Task Learning
Pages 2032 - 2036
Abstract
Multi-task learning (MTL) has been widely applied in online advertising systems. To address the negative transfer issue, recent optimization methods emphasized the gradient alignment of directions or magnitudes. Since prior studies have proven that the shared modules contain both general and specific knowledge, overemphasizing on gradient alignment may crowd out task-specific knowledge. In this paper, we propose a transference-driven approach CoGrad that adaptively maximizes knowledge transference via Coordinated Gradient modification. We explicitly quantify the transference as loss reduction from one task to another, and optimize it to derive an auxiliary gradient. By incorporating this gradient into original task gradients, the model automatically maximizes inter-task transfer and minimizes individual losses, leading to general and specific knowledge harmonization. Besides, we introduce an efficient approximation of the Hessian matrix, making CoGrad computationally efficient. Both offline and online experiments verify that CoGrad significantly outperforms previous methods.
References
[1]
Rich Caruana. 1997. Multitask learning. Machine learning, Vol. 28, 1 (1997), 41--75.
[2]
Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, and Andrew Rabinovich. 2018. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International conference on machine learning. PMLR, 794--803.
[3]
Christopher Fifty, Ehsan Amid, Zhe Zhao, Tianhe Yu, Rohan Anil, and Chelsea Finn. 2021. Efficiently Identifying Task Groupings for Multi-Task Learning. In Neural Information Processing Systems.
[4]
Ruining He and Julian McAuley. 2016. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In proceedings of the 25th international conference on world wide web. 507--517.
[5]
Yun He, Xue Feng, Cheng Cheng, Geng Ji, Yunsong Guo, and James Caverlee. 2022. Metabalance: improving multi-task recommendations via adapting gradient magnitudes of auxiliary tasks. In Proceedings of the ACM Web Conference 2022. 2205--2215.
[6]
Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
[7]
Seanie Lee, Hae Beom Lee, Juho Lee, and Sung Ju Hwang. 2021. Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning. arXiv preprint arXiv:2110.02600 (2021).
[8]
Zihan Lin, Xuanhua Yang, Shaoguo Liu, Xiaoyu Peng, Wayne Xin Zhao, Liang Wang, and Bo Zheng. 2022. Personalized Inter-Task Contrastive Learning for CTR&CVR Joint Estimation. arXiv preprint arXiv:2208.13442 (2022).
[9]
Bo Liu, Xingchao Liu, Xiaojie Jin, Peter Stone, and Qiang Liu. 2021. Conflict-averse gradient descent for multi-task learning. Advances in Neural Information Processing Systems, Vol. 34 (2021), 18878--18890.
[10]
Jiaqi Ma, Zhe Zhao, Xinyang Yi, Jilin Chen, Lichan Hong, and Ed H Chi. 2018b. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 1930--1939.
[11]
Xiao Ma, Liqin Zhao, Guan Huang, Zhi Wang, Zelin Hu, Xiaoqiang Zhu, and Kun Gai. 2018a. Entire space multi-task model: An effective approach for estimating post-click conversion rate. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. 1137--1140.
[12]
Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017).
[13]
Ozan Sener and Vladlen Koltun. 2018. Multi-task learning as multi-objective optimization. Advances in neural information processing systems, Vol. 31 (2018).
[14]
Zirui Wang, Zachary C Lipton, and Yulia Tsvetkov. 2020a. On negative interference in multilingual models: Findings and a meta-learning treatment. arXiv preprint arXiv:2010.03017 (2020).
[15]
Zirui Wang, Yulia Tsvetkov, Orhan Firat, and Yuan Cao. 2020b. Gradient vaccine: Investigating and improving multi-task optimization in massively multilingual models. arXiv preprint arXiv:2010.05874 (2020).
[16]
Penghui Wei, Weimin Zhang, Zixuan Xu, Shaoguo Liu, Kuang-chih Lee, and Bo Zheng. 2021. AutoHERI: Automated Hierarchical Representation Integration for Post-Click Conversion Rate Estimation. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 3528--3532.
[17]
Hong Wen, Jing Zhang, Fuyu Lv, Wentian Bao, Tianyi Wang, and Zulong Chen. 2021. Hierarchically modeling micro and macro behaviors via multi-task learning for conversion rate prediction. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2187--2191.
[18]
Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, and Chelsea Finn. 2020. Gradient surgery for multi-task learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 5824--5836.
[19]
Shuxin Zheng, Qi Meng, Taifeng Wang, Wei Chen, Nenghai Yu, Zhi-Ming Ma, and Tie-Yan Liu. 2017. Asynchronous stochastic gradient descent with delay compensation. In International Conference on Machine Learning. PMLR, 4120--4129.
Index Terms
- Gradient Coordination for Quantifying and Maximizing Knowledge Transference in Multi-Task Learning
Recommendations
MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks
WWW '22: Proceedings of the ACM Web Conference 2022In many personalized recommendation scenarios, the generalization ability of a target task can be improved via learning with additional auxiliary tasks alongside this target task on a multi-task network. However, this method often suffers from a serious ...
MaxGNR: A Dynamic Weight Strategy via Maximizing Gradient-to-Noise Ratio for Multi-task Learning
Computer Vision – ACCV 2022AbstractWhen modeling related tasks in computer vision, Multi-Task Learning (MTL) can outperform Single-Task Learning (STL) due to its ability to capture intrinsic relatedness among tasks. However, MTL may encounter the insufficient training problem, i.e.,...
Metric-Guided Multi-task Learning
Foundations of Intelligent SystemsAbstractMulti-task learning (MTL) aims to solve multiple related learning tasks simultaneously so that the useful information in one specific task can be utilized by other tasks in order to improve the learning performance of all tasks. Many ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
July 2023
3567 pages
ISBN:9781450394086
DOI:10.1145/3539618
- General Chairs:
- Hsin-Hsi Chen,
- Wei-Jou (Edward) Duh,
- Hen-Hsen Huang,
- Program Chairs:
- Makoto P. Kato,
- Josiane Mothe,
- Barbara Poblete
Copyright © 2023 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 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: 18 July 2023
Check for updates
Author Tags
Qualifiers
- Short-paper
Conference
SIGIR '23
Sponsor:
SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval
July 23 - 27, 2023
Taipei, Taiwan
Acceptance Rates
Overall Acceptance Rate 792 of 3,983 submissions, 20%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 79Total Downloads
- Downloads (Last 12 months)46
- Downloads (Last 6 weeks)2
Reflects downloads up to 21 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in