Global-Local Item Embedding for Temporal Set Prediction

被引:3
|
作者
Jung, Seungjae [1 ]
Park, Young-Jin [2 ]
Jeong, Jisu [3 ]
Kim, Kyung-Min [3 ]
Kim, Hiun [4 ]
Kim, Minkyu [4 ]
Kwak, Hanock [4 ]
机构
[1] NAVER CLOVA, Naver R&D Ctr, Seongnam Si, Gyeonggi Do, South Korea
[2] NAVER CLOVA, Naver R&D Ctr, NAVER AI LAB, Seongnam Si, Gyeonggi Do, South Korea
[3] NAVER CLOVA, NAVER AI LAB, Seongnam Si, Gyeonggi Do, South Korea
[4] NAVER CLOVA, Seongnam Si, Gyeonggi Do, South Korea
来源
15TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS 2021) | 2021年
关键词
Temporal Sets; Set Prediction; Tweedie Distribution; Variational Autoencoder;
D O I
10.1145/3460231.3478844
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Temporal set prediction is becoming increasingly important as many companies employ recommender systems in their online businesses, e.g., personalized purchase prediction of shopping baskets. While most previous techniques have focused on leveraging a user's history, the study of combining it with others' histories remains untapped potential. This paper proposes Global-Local Item Embedding (GLOIE) that learns to utilize the temporal properties of sets across whole users as well as within a user by coining the names as global and local information to distinguish the two temporal patterns. GLOIE uses Variational Autoencoder (VAE) and dynamic graph-based model to capture global and local information and then applies attention to integrate resulting item embeddings. Additionally, we propose to use Tweedie output for the decoder of VAE as it can easily model zero-inflated and long-tailed distribution, which is more suitable for several real-world data distributions than Gaussian or multinomial counterparts. When evaluated on three public benchmarks, our algorithm consistently outperforms previous state-of-the-art methods in most ranking metrics.
引用
收藏
页码:674 / 679
页数:6
相关论文
共 50 条
  • [21] Non-rigid Point Set Registration with Global-Local Topology Preservation
    Ge, Song
    Fan, Guoliang
    Ding, Meng
    2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2014, : 245 - 251
  • [22] LEVEL SET TRACKING USING SHAPE PRIOR AND GLOBAL-LOCAL COLOR MODEL
    Heo, Seon
    Cho, Nam Ik
    2015 IEEE INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING APPLICATIONS (ICSIPA), 2015, : 469 - 472
  • [23] The global-local interface and hybridity
    Jaidev, Radhika
    LANGUAGE AND INTERCULTURAL COMMUNICATION, 2015, 15 (02) : 308 - 311
  • [24] Global-local interface in ethnography
    Mathur, Nita
    INDIAN JOURNAL OF SOCIAL WORK, 2006, 67 (1-2): : 119 - 134
  • [25] Global-Local Enrichments in PUMA
    Birner, Matthias
    Schweitzer, Marc Alexander
    MESHFREE METHODS FOR PARTIAL DIFFERENTIAL EQUATIONS IX, 2019, 129 : 167 - 183
  • [26] Genomic Prediction Using Bayesian Regression Models With Global-Local Prior
    Shi, Shaolei
    Li, Xiujin
    Fang, Lingzhao
    Liu, Aoxing
    Su, Guosheng
    Zhang, Yi
    Luobu, Basang
    Ding, Xiangdong
    Zhang, Shengli
    FRONTIERS IN GENETICS, 2021, 12
  • [27] Temporal Sequence of Global-Local Processing in 3-Month-Old Infants
    Frick, Janet E.
    Colombo, John
    Allen, Jennifer Ryther
    INFANCY, 2000, 1 (03) : 375 - 386
  • [28] Video representation learning for temporal action detection using global-local attention
    Tang, Yiping
    Zheng, Yang
    Wei, Chen
    Guo, Kaitai
    Hu, Haihong
    Liang, Jimin
    PATTERN RECOGNITION, 2022, 134
  • [29] Global-local spatio-temporal graph convolutional networks for video summarization
    Wu, Guangli
    Song, Shanshan
    Zhang, Jing
    COMPUTERS & ELECTRICAL ENGINEERING, 2024, 118
  • [30] Mood and Global-Local Focus: Priming a Local Focus Reverses the Link Between Mood and Global-Local Processing
    Huntsinger, Jeffrey R.
    Clore, Gerald L.
    Bar-Anan, Yoav
    EMOTION, 2010, 10 (05) : 722 - 726