Explainable Information Combined Deep Learning to Rank Algorithm

ZHOU Ming-xing

doi:10.3969/j.issn.2096-6091.2024.03.002

您当前的位置：

首页 >

文章列表页 >

Explainable Information Combined Deep Learning to Rank Algorithm

RESEARCH PAPER | 更新时间：2025-04-08

- Explainable Information Combined Deep Learning to Rank Algorithm
- New Generation of Information Technology Vol. 7, Issue 3, Pages: 5-10(2024)
- 作者机构：
  
  达观数据有限公司，上海 200120
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.2096-6091.2024.03.002
  CLC： TP183
- Published：25 March 2024
- 稿件说明：
移动端阅览
周明星. 结合可解释信息的深度学习排序算法[J]. 新一代信息技术, 2024, 7(3): 05-10

ZHOU Ming-xing. Explainable Information Combined Deep Learning to Rank Algorithm[J]. New Generation of Information Technology, 2024, 7(3): 05-10
周明星. 结合可解释信息的深度学习排序算法[J]. 新一代信息技术, 2024, 7(3): 05-10 DOI： 10.3969/j.issn.2096-6091.2024.03.002.

ZHOU Ming-xing. Explainable Information Combined Deep Learning to Rank Algorithm[J]. New Generation of Information Technology, 2024, 7(3): 05-10 DOI： 10.3969/j.issn.2096-6091.2024.03.002.

摘要

在信息爆炸的时代，如何有效地管理和利用海量知识成为了一个关键问题。知识管理系统的核心任务之一是知识利用，搜索是知识利用的主要手段之一，搜索排序效果的好坏，直接影响着对知识的利用效率。现有的机器学习排序算法结合行为、语义及业务特征对排序已有很大的提升，但搜索给定结果排序的原因对于用户是黑盒，这对用户的使用体验影响较大。针对上述问题，本文新设计了一种结合可解释信息的深度学习排序方法（Explainable Information combined Deep Learning To Rank algorithm， EI-DLTR），该方法结合深度学习的强大学习能力，将知识相关的排序理由联合建模排序，在提供用户良好知识排序的同时，提供贴合事实的排序理由，同时也提升了知识排序效果和用户体验。本算法首次将深度学习排序与排序理由建模，并应用在知识搜索领域使用。在与没有考虑排序理由的各同类算法及线上A/B测试中获得了显著增长。

Abstract

In the era of information explosion

effectively managing and utilizing vast amounts of knowledge has become a critical issue. One of the core tasks of knowledge management systems is knowledge utilization

with search being the primary means. The effectiveness of search ranking directly impacts the efficiency of knowledge utilization. Current learning to ranking algorithms have significantly improved rankings by incorporating behavioral

semantic

and business features. However

the reasons behind the given search result rankings are often a black box to users

negatively affecting their experience. To address this issue

this paper proposes an explainable information combined deep learning to rank algorithm (EI-DLTR). This method leverages the powerful learning capabilities of deep learning to jointly model the reasons behind knowledge-related rankings. It provides users with well-ranked knowledge results while offering fact-based explanations for the rankings

thereby improving both knowledge ranking effectiveness and user experience. This algorithm is the first to integrate deep learning to rank with ranking reason and apply it in the field of knowledge search. Significant improvements are achieved in comparisons with similar algorithms that do not consider ranking reasons

as well as in online A/B tests.

关键词

Keywords

references

ALAVI M , LEIDNER D E . Review: Knowledge management and knowledge management systems: Conceptual foundations and research issues [J ] . MIS Quarterly , 2001 , 25 ( 1 ): 107 - 136 .

DAVENPORT T H , PRUSAK L . Working Knowledge: How Organizations Manage What They Know [M ] . Boston : Harvard Business School Press , 2000 .

MAIER R , HADRICH T . Knowledge management systems [M ] // Encyclopedia of knowledge management, Second Edition . IGI Global, 2010 : 779 - 790 .

ALAVI M , LEIDNER D E . Knowledge management systems: Issues, challenges, and benefits [J ] . Communications of the Association for Information systems , 1999 , 1 ( 1 ): 7 .

FRANK U . Knowledge management systems: essential requirements and generic design patterns [C ] // Proceedings of the International Symposium on Information Systems and Engineering ISE'2001 . Las Vegas : CSREA Press , 2001 : 114 - 121 .

QIN T , LIU T Y , XU Y , et al . LETOR: A benchmark collection for research on learning to rank for information retrieval [J ] . Information Retrieval , 2010 , 13 ( 4 ): 346 - 374 .

HERBRICH R , GRAEPEL T , OBERMAYER K . Support vector learning for ordinal regression [J ] . IEE Conference Publication , 1999 , 1 ( 470 ): 97 - 102 .

BURGES C , SHAKED T , RENSHAW E , et al . Learning to rank using gradient descent [C ] // Proceedings of the 22nd international conference on Machine learning . New York : ACM , 2005 : 89 - 96 .

FREUND Y , IYER R D , SCHAPIRE R E , et al . An efficient boosting algorithm for combining preferences [J ] . Journal of Machine Learning Research , 2003 , 4 ( 6 ): 933 - 969 .

BURGES C J C , RAGNO R , LE Q V . Learning to rank with nonsmooth cost functions [C ] // Proceedings of the 19th International Conference on Neural Information Processing Systems . New York : ACM , 2006 : 193 - 200 .

XIA F , LIU T Y , WANG J , et al . Listwise approach to learning to rank: Theory and algorithm [C ] // Proceedings of the 25th international conference on Machine learning . New York : ACM , 2008 : 1192 - 1199 .

CAO Z , QIN T , LIU T Y , et al . Learning to rank: From pairwise approach to listwise approach [C ] // Proceedings of the 24th international conference on Machine learning . New York : ACM , 2007 : 129 - 136 .

IBRAHIM M , CARMAN M . Comparing pointwise and listwise objective functions for random-forest-based learning-to-rank [J ] . ACM Transactions on Information Systems , 2016 , 34 ( 4 ): 1 - 38 .

BURGES C J C . From RankNet to LambdaRank to LambdaMART: An overview [J ] . Learning , 2010 , 11 ( 23-581 ): 81 .

LECUN Y , BOTTOU L , BENGIO Y , et al . Gradient-based learning applied to document recognition [J ] . Proceedings of the IEEE , 1998 , 86 ( 11 ): 2278 - 2324 .

RUMELHART D E , HINTON G E , WILLIAMS R J . Learning representations by back-propagating errors [J ] . Nature , 1986 , 323 ( 6088 ): 533 - 536 .

KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks [J ] . Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 .

HOCHREITER S , SCHMIDHUBER J . Long short-term me- mory [J ] . Neural Computation , 1997 , 9 ( 8 ): 1735 - 1780 .

KINGMA D P , BA J . Adam: A method for stochastic optimization [EB/OL ] . ( 2014 )[2024 ] . http://arxiv.org/abs/1412.6980 http://arxiv.org/abs/1412.6980 .

MNIH V , KAVUKCUOGLU K , SILVER D , et al . Playing atari with deep reinforcement learning [EB/OL ] . ( 2013 )[2024 ] . http://arxiv.org/abs/1312.5602 http://arxiv.org/abs/1312.5602 .

KINGMA D P , WELLING M . Auto-encoding variational Bayes [EB/OL ] . ( 2013 )[2024 ] . http://arxiv.org/abs/1312.6114 http://arxiv.org/abs/1312.6114 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . New York : ACM , 2017 : 6000 - 6010 .

GOODFELLOW I J , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial nets [C ] // Proceedings of the 27th International Conference on Neural Information Processing Systems . New York : ACM , 2014 : 2672 - 2680 .

HUANG P S , HE X D , GAO J F , et al . Learning deep structured semantic models for web search using clickthrough data [C ] // Proceedings of the 22nd ACM international conference on Information & Knowledge Management . New York : ACM , 2013 : 2333 - 2338 .

GUO J F , FAN Y X , AI Q Y , et al . A deep relevance matching model for ad-hoc retrieval [C ] // Proceedings of the 25th ACM International on Conference on Information and Knowledge Management . New York : ACM , 2016 : 55 - 64 .

CHEN Z X , WANG X T , XIE X , et al . Co-attentive multi-task learning for explainable recommendation [C ] // IJCAI . 2019 : 2137 - 2143 .

GAO J Y , WANG X T , WANG Y S , et al . Explainable recommendation through attentive multi-view learning [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2019 , 33 ( 1 ): 3622 - 3629 .

HE X N , CHEN T , KAN M Y , et al . TriRank: Review-aware explainable recommendation by modeling aspects [C ] // Proceedings of the 24th ACM International on Conference on Information and Knowledge Management . New York : ACM , 2015 : 1661 - 1670 .

LI L , ZHANG Y F , CHEN L . Generate neural template explanations for recommendation [C ] // Proceedings of the 29th ACM International Conference on Information & Knowledge Management . New York : ACM , 2020 : 755 - 764

LI P J , WANG Z H , REN Z C , et al . Neural rating regression with abstractive tips generation for recommendation [C ] // Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2017 : 345 - 354 .

WANG X T , CHEN Y R , YANG J , et al . A reinforcement learning framework for explainable recommendation [C ] // 2018 IEEE International Conference on Data Mining (ICDM) . Piscataway : IEEE , 2018 : 587 - 596 .

ZHANG Y F , CHEN X . Explainable recommendation: A survey and new perspectives [J ] . Foundations and Trends® in Information Retrieval , 2020 , 14 ( 1 ): 1 - 101 .

ZHANG Y F , LAI G K , ZHANG M , et al . Explicit factor models for explainable recommendation based on phrase-level sentiment analysis [C ] // Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval . New York : ACM , 2014 : 83 - 92 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Predictive Study of Breast Cancer Pathological Images Based on DenseNet201

Application and Prospect of Deep Learning Technology in Medical Image Analysis

Study on the Recognition of Maize Leaf Disease Based on Deep Learning with Small Sample Size

Study of the Joint Framework for Real-World Super-Resolution-Semantic Segmentation

Classification of Breast Cancer Ultrasound Images Based on GoogLeNet

Related Author

GAO Ming-ze

HAN Yang

CHEN Guang-xin

GUO Jin-xing

SUN Yue

MIAO Zhuang

FU Li-yao

LIU Li-bing

Related Institution

Hongqi Hospital Affiliated with Mudanjiang Medical University

Basic Medical College of Mudanjiang Medical University

Medical Imaging College of Mudanjiang Medical University

Chongqing Communication Design Institute Co., Ltd

Henan Agricultural University ， College of Information and Mangement Science

⁰