Item Tagging for Information Retrieval: A Tripartite Graph Neural Network based Approach

被引:8
|
作者
Mao, Kelong [1 ]
Xiao, Xi [2 ]
Zhu, Jieming [3 ]
Lu, Biao [3 ]
Tang, Ruiming [3 ]
He, Xiuqiang [3 ]
机构
[1] Tsinghua Univ, Huawei Noahs Ark Lab, Beijing, Peoples R China
[2] Tsinghua Univ, Pengcheng Lab, Beijing, Peoples R China
[3] Huawei Noahs Ark Lab, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
Information retrieval; item tagging; graph neural networks;
D O I
10.1145/3397271.3401438
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Tagging has been recognized as a successful practice to boost relevance matching for information retrieval (IR), especially when items lack rich textual descriptions. A lot of research has been done for either multi-label text categorization or image annotation. However, there is a lack of published work that targets at item tagging specifically for IR. Directly applying a traditional multi-label classification model for item tagging is sub-optimal, due to the ignorance of unique characteristics in IR. In this work, we propose to formulate item tagging as a link prediction problem between item nodes and tag nodes. To enrich the representation of items, we leverage the query logs available in IR tasks, and construct a query-item-tag tripartite graph. This formulation results in a TagGNN model that utilizes heterogeneous graph neural networks with multiple types of nodes and edges. Different from previous research, we also optimize both full tag prediction and partial tag completion cases in a unified framework via a primary-dual loss mechanism. Experimental results on both open and industrial datasets show that our TagGNN approach outperforms the state-of-the-art multi-label classification approaches.
引用
收藏
页码:2327 / 2336
页数:10
相关论文
共 50 条
  • [1] Improving Similar Question Retrieval using a Novel Tripartite Neural Network based Approach
    Sen, Anirban
    Sinha, Manjira
    Mannarswamy, Sandya
    [J]. PROCEEDINGS OF THE 9TH ANNUAL MEETING OF THE FORUM FOR INFORMATION RETRIEVAL EVALUATION (FIRE 2017), 2017, : 1 - 5
  • [2] ATGNN: Audio Tagging Graph Neural Network
    Singh, Shubhr
    Steinmetz, Christian J.
    Benetos, Emmanouil
    Phan, Huy
    Stowell, Dan
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2024, 31 : 825 - 829
  • [3] Multi-agent Web information retrieval: Neural network based approach
    Choi, YS
    Yoo, SI
    [J]. ADVANCES IN INTELLIGENT DATA ANALYSIS, PROCEEDINGS, 1999, 1642 : 499 - 511
  • [4] Intelligent Big Information Retrieval of Smart Library Based on Graph Neural Network (GNN) Algorithm
    Pang, Lu
    [J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
  • [5] Graph-ICF: Item-based collaborative filtering based on graph neural network
    Liu, Meng
    Li, Jianjun
    Liu, Ke
    Wang, Chaoyang
    Peng, Pan
    Li, Guohui
    Cheng, Yongjing
    Jia, Guohui
    Xie, Wei
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 251
  • [6] A neural network-based information retrieval system
    Tian, YL
    Xiong, SB
    [J]. ICEMI'2003: PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON ELECTRONIC MEASUREMENT & INSTRUMENTS, VOLS 1-3, 2003, : 1998 - 2001
  • [7] A hybrid neural network approach to combine textual information and rating information for item recommendation
    Donghua Liu
    Jing Li
    Bo Du
    Jun Chang
    Rong Gao
    Yujia Wu
    [J]. Knowledge and Information Systems, 2021, 63 : 621 - 646
  • [8] A hybrid neural network approach to combine textual information and rating information for item recommendation
    Liu, Donghua
    Li, Jing
    Du, Bo
    Chang, Jun
    Gao, Rong
    Wu, Yujia
    [J]. KNOWLEDGE AND INFORMATION SYSTEMS, 2021, 63 (03) : 621 - 646
  • [9] Global and session item graph neural network for session-based recommendation
    Sheng, Jinfang
    Zhu, Jiafu
    Wang, Bin
    Long, Zhendan
    [J]. APPLIED INTELLIGENCE, 2023, 53 (10) : 11737 - 11749
  • [10] Global and session item graph neural network for session-based recommendation
    Jinfang Sheng
    Jiafu Zhu
    Bin Wang
    Zhendan Long
    [J]. Applied Intelligence, 2023, 53 : 11737 - 11749