iHAS: Instance-wise Hierarchical Architecture Search for Deep Learning Recommendation Models

被引:0
|
作者
Yu, Yakun [1 ]
Qi, Shi-Ang [1 ]
Yang, Jiuding [1 ]
Jiang, Liyao [1 ]
Niu, Di [1 ]
机构
[1] Univ Alberta, Edmonton, AB, Canada
关键词
recommender system; instance-wise; embedding dimension search;
D O I
10.1145/3583780.3614925
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Current recommender systems employ large-sized embedding tables with uniform dimensions for all features, leading to overfitting, high computational cost, and suboptimal generalizing performance. Many techniques aim to solve this issue by feature selection or embedding dimension search. However, these techniques typically select a fixed subset of features or embedding dimensions for all instances and feed all instances into one recommender model without considering heterogeneity between items or users. This paper proposes a novel instance-wise Hierarchical Architecture Search framework, iHAS, which automates neural architecture search at the instance level. Specifically, iHAS incorporates three stages: searching, clustering, and retraining. The searching stage identifies optimal instance-wise embedding dimensions across different field features via carefully designed Bernoulli gates with stochastic selection and regularizers. After obtaining these dimensions, the clustering stage divides samples into distinct groups via a deterministic selection approach of Bernoulli gates. The retraining stage then constructs different recommender models, each one designed with optimal dimensions for the corresponding group. We conduct extensive experiments to evaluate the proposed iHAS on two public benchmark datasets from a real-world recommender system. The experimental results demonstrate the effectiveness of iHAS and its outstanding transferability to widely-used deep recommendation models.
引用
收藏
页码:3030 / 3039
页数:10
相关论文
共 50 条
  • [31] FINCH: Enhancing Federated Learning With Hierarchical Neural Architecture Search
    Liu, Jianchun
    Yan, Jiaming
    Xu, Hongli
    Wang, Zhiyuan
    Huang, Jinyang
    Xu, Yang
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (05) : 6012 - 6026
  • [32] MULTIPLE INSTANCE LEARNING VIA DEEP HIERARCHICAL EXPLORATION FOR HISTOLOGY IMAGE CLASSIFICATION
    Hering, Jan
    Kybic, Jan
    2020 IEEE 17TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2020), 2020, : 235 - 238
  • [33] Spatial-Aware Hierarchical Collaborative Deep Learning for POI Recommendation
    Yin, Hongzhi
    Wang, Weiqing
    Wang, Hao
    Chen, Ling
    Zhou, Xiaofang
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2017, 29 (11) : 2537 - 2551
  • [34] Automated Deep Learning: Neural Architecture Search Is Not the End
    Dong, Xuanyi
    Kedziora, David Jacob
    Musial, Katarzyna
    Gabrys, Bogdan
    FOUNDATIONS AND TRENDS IN MACHINE LEARNING, 2024, 17 (05): : 767 - 920
  • [35] Learning deep morphological networks with neural architecture search
    Hu, Yufei
    Belkhir, Nacim
    Angulo, Jesus
    Yao, Angela
    Franchi, Gianni
    PATTERN RECOGNITION, 2022, 131
  • [36] Differential Architecture Search in Deep Learning for Genomic Applications
    Moosa, Shabir
    Boughorbel, Sabri
    Amira, Abbes
    2019 IEEE 10TH GCC CONFERENCE & EXHIBITION (GCC), 2019,
  • [37] STD-NET: Search of Image Steganalytic Deep-Learning Architecture via Hierarchical Tensor Decomposition
    Tan, Shunquan
    Li, Qiushi
    Li, Laiyuan
    Li, Bin
    Huang, Jiwu
    IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING, 2023, 20 (03) : 2657 - 2673
  • [38] Deep Learning Based Search and Recommendation of Literature in Wanfang Knowledge Base
    Northwest Minzu University, School of Mathematics and Computer Science, Lanzhou, Gansu
    730030, China
    IEEE Int. Conf. Intell. Comput. Signal Process., ICSP, 2021, (781-785):
  • [39] DeepCrack: A deep hierarchical feature learning architecture for crack segmentation
    Liu, Yahui
    Yao, Jian
    Lu, Xiaohu
    Xie, Renping
    Li, Li
    NEUROCOMPUTING, 2019, 338 : 139 - 153
  • [40] A hierarchical and regional deep learning architecture for image description generation
    Kinghorn, Philip
    Zhang, Li
    Shao, Ling
    PATTERN RECOGNITION LETTERS, 2019, 119 : 77 - 85