Unified conversational recommendation policy learning via graph-based reinforcement learning
Conversational recommender systems (CRS) enable the traditional recommender systems to explicitly acquire user preferences towards items and attributes through interactive conversations. Reinforcement learning (RL) is widely adopted to learn conversational recommendation policies to decide what attr...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9114 https://ink.library.smu.edu.sg/context/sis_research/article/10117/viewcontent/3404835.3462913.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-10117 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-101172024-08-01T14:42:58Z Unified conversational recommendation policy learning via graph-based reinforcement learning DENG, Yang LI, Yaliang SUN, Fei DING, Bolin LAM, Wai Conversational recommender systems (CRS) enable the traditional recommender systems to explicitly acquire user preferences towards items and attributes through interactive conversations. Reinforcement learning (RL) is widely adopted to learn conversational recommendation policies to decide what attributes to ask, which items to recommend, and when to ask or recommend, at each conversation turn. However, existing methods mainly target at solving one or two of these three decision-making problems in CRS with separated conversation and recommendation components, which restrict the scalability and generality of CRS and fall short of preserving a stable training procedure. In the light of these challenges, we propose to formulate these three decision-making problems in CRS as a unified policy learning task. In order to systematically integrate conversation and recommendation components, we develop a dynamic weighted graph based RL method to learn a policy to select the action at each conversation turn, either asking an attribute or recommending items. Further, to deal with the sample efficiency issue, we propose two action selection strategies for reducing the candidate action space according to the preference and entropy information. Experimental results on two benchmark CRS datasets and a real-world E-Commerce application show that the proposed method not only significantly outperforms state-of-the-art methods but also enhances the scalability and stability of CRS. 2021-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9114 info:doi/10.1145/3404835.3462913 https://ink.library.smu.edu.sg/context/sis_research/article/10117/viewcontent/3404835.3462913.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Conversational Recommendation Reinforcement Learning Graph Representation Learning Databases and Information Systems Graphics and Human Computer Interfaces |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Conversational Recommendation Reinforcement Learning Graph Representation Learning Databases and Information Systems Graphics and Human Computer Interfaces |
spellingShingle |
Conversational Recommendation Reinforcement Learning Graph Representation Learning Databases and Information Systems Graphics and Human Computer Interfaces DENG, Yang LI, Yaliang SUN, Fei DING, Bolin LAM, Wai Unified conversational recommendation policy learning via graph-based reinforcement learning |
description |
Conversational recommender systems (CRS) enable the traditional recommender systems to explicitly acquire user preferences towards items and attributes through interactive conversations. Reinforcement learning (RL) is widely adopted to learn conversational recommendation policies to decide what attributes to ask, which items to recommend, and when to ask or recommend, at each conversation turn. However, existing methods mainly target at solving one or two of these three decision-making problems in CRS with separated conversation and recommendation components, which restrict the scalability and generality of CRS and fall short of preserving a stable training procedure. In the light of these challenges, we propose to formulate these three decision-making problems in CRS as a unified policy learning task. In order to systematically integrate conversation and recommendation components, we develop a dynamic weighted graph based RL method to learn a policy to select the action at each conversation turn, either asking an attribute or recommending items. Further, to deal with the sample efficiency issue, we propose two action selection strategies for reducing the candidate action space according to the preference and entropy information. Experimental results on two benchmark CRS datasets and a real-world E-Commerce application show that the proposed method not only significantly outperforms state-of-the-art methods but also enhances the scalability and stability of CRS. |
format |
text |
author |
DENG, Yang LI, Yaliang SUN, Fei DING, Bolin LAM, Wai |
author_facet |
DENG, Yang LI, Yaliang SUN, Fei DING, Bolin LAM, Wai |
author_sort |
DENG, Yang |
title |
Unified conversational recommendation policy learning via graph-based reinforcement learning |
title_short |
Unified conversational recommendation policy learning via graph-based reinforcement learning |
title_full |
Unified conversational recommendation policy learning via graph-based reinforcement learning |
title_fullStr |
Unified conversational recommendation policy learning via graph-based reinforcement learning |
title_full_unstemmed |
Unified conversational recommendation policy learning via graph-based reinforcement learning |
title_sort |
unified conversational recommendation policy learning via graph-based reinforcement learning |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2021 |
url |
https://ink.library.smu.edu.sg/sis_research/9114 https://ink.library.smu.edu.sg/context/sis_research/article/10117/viewcontent/3404835.3462913.pdf |
_version_ |
1814047745799880704 |