Please use this identifier to cite or link to this item: https://dspace.ctu.edu.vn/jspui/handle/123456789/81783
Title: Dual transformer encoders for session-based recommendation
Authors: Pham, Hoang Anh
Ngo, Xuan Bach
Tu, Minh Phuong
Keywords: Recommender systems
Session-based recommendation
Self-attention
Dual Transformer
Issue Date: 2021
Series/Report no.: Journal of Computer Science and Cybernetics;Vol.37, No.04 .- P.511-527
Abstract: When long-term user profiles are not available, session-based recommendation methods are used to predict the user's next actions from anonymous sessions-based data. Recent advances in session-based recommendation highlight the necessity of modeling not only user sequential behaviors but also the user's main interest in a session, while avoiding the effect of unintended clicks causing interest drift of the user. In this work, we propose a Dual Transformer Encoder Recommendation model (DTER) as a solution to address this requirement. The idea is to combine the following recipes: (1) A Transformer-based model with dual encoders capable of modeling both sequential patterns and the main interest of the user in a session; (2) A new recommendation model that is designed for learning richer session contexts by conditioning on all permutations of the session prefix. This approach provides a unified framework for leveraging the ability of the Transformer's self-attention mechanism in modeling session sequences while taking into account the user's main interest in the session. We empirically evaluate the proposed method on two benchmark datasets. The results show that DTER outperforms state-of-the-art session-based recommendation methods on common evaluation metrics.
URI: https://dspace.ctu.edu.vn/jspui/handle/123456789/81783
ISSN: 1813-9663
Appears in Collections:Tin học và Điều khiển học (Journal of Computer Science and Cybernetics)

Files in This Item:
File Description SizeFormat 
_file_
  Restricted Access
3.48 MBAdobe PDF
Your IP: 3.147.48.226


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.