The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
Open accessAbstract
Neural-based multi-task learning has been successfully used in many real-world large-scale applications such as recommendation systems. For example, in movie recommendations, beyond providing users movies which they tend to purchase and watch, the system might also optimize for users liking the movies afterwards. With multi-task learning, we aim to build a single model that learns these multiple goals and tasks simultaneously. However, the prediction quality of commonly used multi-task models is often sensitive to the relationships between tasks. It is therefore important to study the modeling tradeoffs between task-specific objectives and inter-task relationships. In this work, we propose a novel multi-task learning approach, Multi-gate Mixture-of-Experts (MMoE), which explicitly learns to model task relationships from data. We adapt the Mixture-of-Experts (MoE) structure to multi-task learning by sharing the expert submodels across all tasks, while also having a gating network trained to optimize each task. To validate our approach on data with different levels of task relatedness, we first apply it to a synthetic dataset where we control the task relatedness. We show that the proposed approach performs better than baseline methods when the tasks are less related. We also show that the MMoE structure results in an additional trainability benefit, depending on different levels of randomness in the training data and model initialization. Furthermore, we demonstrate the performance improvements by MMoE on real tasks including a binary classification benchmark, and a large-scale content recommendation system at Google.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 25,410
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
(2010) · Cited by 14,134
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408
Practical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691
Adaptive Mixtures of Local Experts
Jacobs, R. A., Jordan, M. I., Nowlan, S. J., & Hinton, G. E. (1991) · Neural Computation · doi:10.1162/neco.1991.3.1.79 · Cited by 5,384
Large Scale Distributed Deep Networks
Dean, J. B., Corrado, G. S., Monga, R., Chen, K., Devin, M., Mao, M., Ranzato, M., Senior, A., Tucker, P. A., Yang, K., et al. (2012) · neural information processing systems · Cited by 4,489
Deep Neural Networks for YouTube Recommendations
Covington, P., Adams, J., & Sargin, E. (2016) · Proceedings of the 10th ACM Conference on Recommender Systems · doi:10.1145/2959100.2959190 · Cited by 3,539
An Overview of Multi-Task Learning in Deep Neural Networks
Ruder, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.05098 · Cited by 2,265
Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
Bengio, Y., Léonard, N., & Courville, A. (2013) · arXiv · doi:10.48550/arxiv.1308.3432 · Cited by 1,910
Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
Johnson, M., Schuster, M., Le, Q. V., Krikun, M., Wu, Y., Chen, Z., Thorat, N., Viégas, F., Wattenberg, M., Corrado, G., et al. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00065 · Cited by 1,747
Cross-Stitch Networks for Multi-task Learning
Misra, I., Shrivastava, A., Gupta, A., & Hebert, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.433 · Cited by 1,397
Caruana, R. (1998) · Cited by 1,110
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., & Dean, J. (2017) · arXiv · doi:10.48550/arxiv.1701.06538 · Cited by 933
A Model of Inductive Bias Learning
Baxter, J. (2000) · Cited by 730
Multitask Learning: A Knowledge-Based Source of Inductive Bias
Caruana, R. A. (1993) · Machine Learning Proceedings 1993 · doi:10.1016/b978-1-55860-307-3.50012-5 · Cited by 679
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
Fernando, C., Banarse, D., Blundell, C., Zwólš, Y., Ha, D., Rusu, A. A., Pritzel, A., & Wierstra, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.08734 · Cited by 591
A model of inductive bias learning
Baxter, J. (2000) · Journal of Artificial Intelligence Research · doi:10.1613/jair.731 · Cited by 582
Exploiting Task Relatedness for Multiple Task Learning
Ben-David, S., & Schuller, R. (2003) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-45167-9_41 · Cited by 425
Learning Factored Representations in a Deep Mixture of ExpertsPreprint
Eigen, D., Ranzato, M., & Sutskever, I. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.4314 · Cited by 417
Low Resource Dependency Parsing: Cross-lingual Parameter Sharing in a Neural Network Parser
Duong, L., Cohn, T., Bird, S., & Cook, P. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) · doi:10.3115/v1/p15-2139 · Cited by 402
Learning with Whom to Share in Multi-task Feature Learning
Kang, Z., Grauman, K. L., & Sha, F. (2011) · Cited by 320
Ask the GRU: Multi-task Learning for Deep Text Recommendations
Bansal, T., Belanger, D., & McCallum, A. (2016) · Proceedings of the 10th ACM Conference on Recommender Systems · doi:10.1145/2959100.2959180 · Cited by 306
Capacity and Trainability in Recurrent Neural NetworksPreprint
Collins, J., Sohl‐Dickstein, J., & Sussillo, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.09913 · Cited by 195
Improving User Topic Interest Profiles by Behavior Factorization
Zhao, Z., Cheng, Z., Hong, L., & Ed, H. (2015) · International World Wide Web Conference (WWW) · doi:10.1145/2736277.2741656 · Cited by 194
Self-citationLow-Rank Approximations for Conditional Feedforward Computation in Deep Neural NetworksPreprint
Davis, A., & Arel, I. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.4461 · Cited by 92
Learning Structured Weight Uncertainty in Bayesian Neural Networks
Sun, S., Chen, C., & Carin, L. (2017) · International Conference on Artificial Intelligence and Statistics · Cited by 84
A theoretical framework for learning from a pool of disparate data sources
Ben-David, S., Gehrke, J. E., & Schuller, R. (2002) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/775047.775111 · Cited by 69
A model of inductive bias learning
BaxterJonathan (2000) · doi:10.5555/1622248.1622254 · Cited by 24
Cited by
A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions
Gao, C., Zheng, Y., Li, N., Li, Y., Qin, Y., Piao, J., Quan, Y., Chang, J., Jin, D., He, X., et al. (2023) · ACM Transactions on Recommender Systems · doi:10.1145/3568022 · Cited by 1,082
Dynamic Neural Networks: A Survey
Han, Y., Huang, G., Song, S., Yang, L., Wang, H., & Wang, Y. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3117837 · Cited by 848
Multi-Task Learning for Dense Prediction Tasks: A Survey
Vandenhende, S., Georgoulis, S., Van Gansbeke, W., Proesmans, M., Dai, D., & Van Gool, L. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3054719 · Cited by 840
Tang, H., Liu, J., Zhao, M., & Gong, X. (2020) · Fourteenth ACM Conference on Recommender Systems · doi:10.1145/3383313.3412236 · Cited by 631
DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems
Wang, R., Shivanna, R., Cheng, D., Jain, S., Lin, D., Hong, L., & Chi, E. (2021) · Proceedings of the Web Conference 2021 · doi:10.1145/3442381.3450078 · Cited by 568
Self-citation
Metadata
- Authors
- Ma, J., Zhao, Z., Yi, X., Chen, J., Hong, L., & Chi, E. H.
- Venue
- Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
- Publisher
- ACM
- Published
- 2018-07-19
- Pages
- 1930-1939
- OpenAlex
- W2809290718
- Cited by
- 1,233
- References
- 32
- FWCI
- 13.63
- Type
- conference paper
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.