CPMR: context-aware incremental sequential recommendation with pseudo-multi-task learning
The motivations of users to make interactions can be divided into static preference and dynamic interest. To accurately model user representations over time, recent studies in sequential recommendation utilize information propagation and evolution to mine from batches of arriving interactions. Howev...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/170988 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-170988 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1709882023-10-27T15:35:39Z CPMR: context-aware incremental sequential recommendation with pseudo-multi-task learning Bian, Qingtian Xu, Jiaxing Fang, Hui Ke, Yiping School of Computer Science and Engineering 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023) Computational Intelligence Laboratory (CIL) Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Recommender Systems Incremental Recommendation Context-Aware Recommendation Graph Neural Networks Pseudo-Multi-Task Learning The motivations of users to make interactions can be divided into static preference and dynamic interest. To accurately model user representations over time, recent studies in sequential recommendation utilize information propagation and evolution to mine from batches of arriving interactions. However, they ignore the fact that people are easily influenced by the recent actions of other users in the contextual scenario, and applying evolution across all historical interactions dilutes the importance of recent ones, thus failing to model the evolution of dynamic interest accurately. To address this issue, we propose a Context-Aware Pseudo-Multi-Task Recommender System (CPMR) to model the evolution in both historical and contextual scenarios by creating three representations for each user and item under different dynamics: static embedding, historical temporal states, and contextual temporal states. To dually improve the performance of temporal states evolution and incremental recommendation, we design a Pseudo-Multi-Task Learning (PMTL) paradigm by stacking the incremental single-target recommendations into one multi-target task for joint optimization. Within the PMTL paradigm, CPMR employs a shared-bottom network to conduct the evolution of temporal states across historical and contextual scenarios, as well as the fusion of them at the user-item level. In addition, CPMR incorporates one real tower for incremental predictions, and two pseudo towers dedicated to updating the respective temporal states based on new batches of interactions. Experimental results on four benchmark recommendation datasets show that CPMR consistently outperforms state-of-the-art baselines and achieves significant gains on three of them. The source code is available at https://github.com/DiMarzioBian/CPMR. Ministry of Education (MOE) National Research Foundation (NRF) Published version This research/project is supported by the Ministry of Education, Singapore under its MOE Academic Research Fund Tier 2 (STEM RIE2025 Award MOE-T2EP20220-0006), and the National Research Foundation, Singapore under its Industry Alignment Fund – Prepositioning (IAF-PP) Funding Initiative. 2023-10-27T01:12:55Z 2023-10-27T01:12:55Z 2023 Conference Paper Bian, Q., Xu, J., Fang, H. & Ke, Y. (2023). CPMR: context-aware incremental sequential recommendation with pseudo-multi-task learning. 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023), October 2023, 120-130. https://dx.doi.org/10.1145/3583780.3615512 979-8-4007-0124-5/23/10 https://hdl.handle.net/10356/170988 10.1145/3583780.3615512 October 2023 120 130 en MOE-T2EP20220-0006 IAF-PP © 2023 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution International 4.0 License. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Recommender Systems Incremental Recommendation Context-Aware Recommendation Graph Neural Networks Pseudo-Multi-Task Learning |
spellingShingle |
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Recommender Systems Incremental Recommendation Context-Aware Recommendation Graph Neural Networks Pseudo-Multi-Task Learning Bian, Qingtian Xu, Jiaxing Fang, Hui Ke, Yiping CPMR: context-aware incremental sequential recommendation with pseudo-multi-task learning |
description |
The motivations of users to make interactions can be divided into static preference and dynamic interest. To accurately model user representations over time, recent studies in sequential recommendation utilize information propagation and evolution to mine from batches of arriving interactions. However, they ignore the fact that people are easily influenced by the recent actions of other users in the contextual scenario, and applying evolution across all historical interactions dilutes the importance of recent ones, thus failing to model the evolution of dynamic interest accurately. To address this issue, we propose a Context-Aware Pseudo-Multi-Task Recommender System (CPMR) to model the evolution in both historical and contextual scenarios by creating three representations for each user and item under different dynamics: static embedding, historical temporal states, and contextual temporal states. To dually improve the performance of temporal states evolution and incremental recommendation, we design a Pseudo-Multi-Task Learning
(PMTL) paradigm by stacking the incremental single-target recommendations into one multi-target task for joint optimization. Within the PMTL paradigm, CPMR employs a shared-bottom network to conduct the evolution of temporal states across historical and contextual scenarios, as well as the fusion of them at the user-item level. In addition, CPMR incorporates one real tower for incremental predictions, and two pseudo towers dedicated to updating the respective temporal states based on new batches of interactions.
Experimental results on four benchmark recommendation datasets show that CPMR consistently outperforms state-of-the-art baselines and achieves significant gains on three of them. The source code is available at https://github.com/DiMarzioBian/CPMR. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Bian, Qingtian Xu, Jiaxing Fang, Hui Ke, Yiping |
format |
Conference or Workshop Item |
author |
Bian, Qingtian Xu, Jiaxing Fang, Hui Ke, Yiping |
author_sort |
Bian, Qingtian |
title |
CPMR: context-aware incremental sequential recommendation with pseudo-multi-task learning |
title_short |
CPMR: context-aware incremental sequential recommendation with pseudo-multi-task learning |
title_full |
CPMR: context-aware incremental sequential recommendation with pseudo-multi-task learning |
title_fullStr |
CPMR: context-aware incremental sequential recommendation with pseudo-multi-task learning |
title_full_unstemmed |
CPMR: context-aware incremental sequential recommendation with pseudo-multi-task learning |
title_sort |
cpmr: context-aware incremental sequential recommendation with pseudo-multi-task learning |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/170988 |
_version_ |
1781793797185732608 |