Draft:Tensorflow Ranking
| Submission declined on 22 April 2025 by Miminity (talk). This submission is not adequately supported by reliable sources. Reliable sources are required so that information can be verified. If you need help with referencing, please see Referencing for beginners and Citing sources.
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|  |
Comment: Source 1, 9 & 2 is primary. Also this draft is a WP:DEADEND. Warm Regards, Miminity (Talk?) (me contribs) 13:24, 22 April 2025 (UTC)
TensorFlow Ranking is an open-source library developed by Google for creating scalable neural learning to rank (LTR) models..[1] Built on top of TensorFlow, it focuses on ranking tasks where the goal is to order a list of items based on relevance, typically in response to a user query.[2] The library is widely used in search engines, recommendation systems, and other applications requiring optimized item ordering.
History
[edit]TensorFlow Ranking was first introduced in a paper titled "TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank", published on arXiv in November 2018, with a revised version in May 2019.[3] The paper, authored by research leads Michael Bendersky, Rohan Anil, Jan Pfeifer, Stephan Wolf and colleagues at Google, was presented at several major conferences including SIGIR 2019, ICTIR 2019, and KDD 2019. The library was released as an open-source project on GitHub to facilitate community contributions and wider adoption.[2]
Features
[edit]TensorFlow Ranking leverages TensorFlow's scalability and the Keras API for model construction. The library is designed to handle millions of data points and process heterogeneous dense and sparse features.[1]
Key features include:
- Multiple ranking approaches: Supports pointwise, pairwise, and listwise loss functions
- Evaluation metrics: Includes Mean Reciprocal Rank (MRR) and Normalized Discounted Cumulative Gain (NDCG)
- Distributed training: Supports various distribution strategies for scalable implementation
- Pipeline utilities: Offers end-to-end ranking workflows from data processing to deployment
- Advanced techniques: Includes support for TFR-BERT and neural ranking GAMs[1]
Applications
[edit]The primary applications of TensorFlow Ranking are in search and recommendation systems, with notable implementations in Gmail and Google Drive for ranking emails and files.[3] Additional applications include machine translation[4], dialogue systems[5], e-commerce [6], smart city planning[7], and computational biology[8]
Development
[edit]TensorFlow Ranking was primarily developed by a team at Google, led by key researchers Michael Bendersky, Jan Pfeiffer, Rohan Anil and Stephan Wolf, who also authored the original research paper introducing the library.[2][3]
See also
[edit]References
[edit]- ^ a b c "TensorFlow Ranking homepage".
- ^ a b c "Tensorflow/Ranking Readme". GitHub.
- ^ a b c Pasumarthi, Rama Kumar; Bruch, Sebastian; Wang, Xuanhui; Li, Cheng; Bendersky, Michael; Najork, Marc; Pfeifer, Jan; Golbandi, Nadav; Anil, Rohan (2019-05-17), "TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank", Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2970–2978, doi:10.1145/3292500.3330677, ISBN 978-1-4503-6201-6
- ^ Chen, Huadong; Huang, Shujian; Chiang, David; Dai, Xinyu; Chen, Jiajun (2017-06-17). "Top-Rank Enhanced Listwise Optimization for Statistical Machine Translation". In Levy, Roger; Specia, Lucia (eds.). Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017). Vancouver, Canada: Association for Computational Linguistics. pp. 90–99. doi:10.18653/v1/K17-1011.
- ^ Yang, Liu; Qiu, Minghui; Qu, Chen; Guo, Jiafeng; Zhang, Yongfeng; Croft, W. Bruce; Huang, Jun; Chen, Haiqing (2018-05-09), "Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems", The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 245–254, doi:10.1145/3209978.3210011, ISBN 978-1-4503-5657-2
- ^ Magnani, Alessandro; Liu, Feng; Xie, Min; Banerjee, Somnath (2019-05-13). "Neural Product Retrieval at Walmart.com". Companion Proceedings of the 2019 World Wide Web Conference. WWW '19. New York, NY, USA: Association for Computing Machinery. pp. 367–372. doi:10.1145/3308560.3316603. ISBN 978-1-4503-6675-5.
- ^ Yuan, Yukun; Ma, Meiyi; Han, Songyang; Zhang, Desheng; Miao, Fei; Stankovic, John; Lin, Shan (2021-05-19). "DeResolver: A decentralized negotiation and conflict resolution framework for smart city services". Proceedings of the ACM/IEEE 12th International Conference on Cyber-Physical Systems. ICCPS '21. New York, NY, USA: Association for Computing Machinery. pp. 98–109. doi:10.1145/3450267.3450538. ISBN 978-1-4503-8353-0.
- ^ Liu, Bin; Chen, Junjie; Wang, Xiaolong (2015-11-01). "Application of learning to rank to protein remote homology detection". Bioinformatics (Oxford, England). 31 (21): 3492–3498. doi:10.1093/bioinformatics/btv413. ISSN 1367-4811. PMID 26163693.