Explanation guided contrastive learning for sequential recommendation
Recently, contrastive learning has been applied to the sequential recommendation task to address data sparsity caused by users with few item interactions and items with few user adoptions. Nevertheless, the existing contrastive learning-based methods fail to ensure that the positive (or negative) se...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/lkcsb_research/7084 https://ink.library.smu.edu.sg/context/lkcsb_research/article/8083/viewcontent/2209.01347.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.lkcsb_research-8083 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.lkcsb_research-80832024-04-18T06:15:32Z Explanation guided contrastive learning for sequential recommendation WANG, Lei LIM, Ee-peng LIU, Zhiwei ZHAO, Tianxiang Recently, contrastive learning has been applied to the sequential recommendation task to address data sparsity caused by users with few item interactions and items with few user adoptions. Nevertheless, the existing contrastive learning-based methods fail to ensure that the positive (or negative) sequence obtained by some random augmentation (or sequence sampling) on a given anchor user sequence remains to be semantically similar (or different). When the positive and negative sequences turn out to be false positive and false negative respectively, it may lead to degraded recommendation performance. In this work, we address the above problem by proposing Explanation Guided Augmentations (EGA) and Explanation Guided Contrastive Learning for Sequential Recommendation (EC4SRec) model framework. The key idea behind EGA is to utilize explanation method(s) to determine items’ importance in a user sequence and derive the positive and negative sequences accordingly. EC4SRec then combines both self-supervised and supervised contrastive learning over the positive and negative sequences generated by EGA operations to improve sequence representation learning for more accurate recommendation results. Extensive experiments on four real-world benchmark datasets demonstrate that EC4SRec outperforms the state-of-the-art sequential recommendation methods and two recent contrastive learning-based sequential recommendation methods, CL4SRec and DuoRec. Our experiments also show that EC4SRec can be easily adapted for different sequence encoder backbones (e.g., GRU4Rec and Caser), and improve their recommendation performance 2022-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/lkcsb_research/7084 info:doi/10.1145/3511808.3557317 https://ink.library.smu.edu.sg/context/lkcsb_research/article/8083/viewcontent/2209.01347.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection Lee Kong Chian School Of Business eng Institutional Knowledge at Singapore Management University Sequential Recommendation Contrastive Learning Explanation Databases and Information Systems Numerical Analysis and Scientific Computing |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Sequential Recommendation Contrastive Learning Explanation Databases and Information Systems Numerical Analysis and Scientific Computing |
spellingShingle |
Sequential Recommendation Contrastive Learning Explanation Databases and Information Systems Numerical Analysis and Scientific Computing WANG, Lei LIM, Ee-peng LIU, Zhiwei ZHAO, Tianxiang Explanation guided contrastive learning for sequential recommendation |
description |
Recently, contrastive learning has been applied to the sequential recommendation task to address data sparsity caused by users with few item interactions and items with few user adoptions. Nevertheless, the existing contrastive learning-based methods fail to ensure that the positive (or negative) sequence obtained by some random augmentation (or sequence sampling) on a given anchor user sequence remains to be semantically similar (or different). When the positive and negative sequences turn out to be false positive and false negative respectively, it may lead to degraded recommendation performance. In this work, we address the above problem by proposing Explanation Guided Augmentations (EGA) and Explanation Guided Contrastive Learning for Sequential Recommendation (EC4SRec) model framework. The key idea behind EGA is to utilize explanation method(s) to determine items’ importance in a user sequence and derive the positive and negative sequences accordingly. EC4SRec then combines both self-supervised and supervised contrastive learning over the positive and negative sequences generated by EGA operations to improve sequence representation learning for more accurate recommendation results. Extensive experiments on four real-world benchmark datasets demonstrate that EC4SRec outperforms the state-of-the-art sequential recommendation methods and two recent contrastive learning-based sequential recommendation methods, CL4SRec and DuoRec. Our experiments also show that EC4SRec can be easily adapted for different sequence encoder backbones (e.g., GRU4Rec and Caser), and improve their recommendation performance |
format |
text |
author |
WANG, Lei LIM, Ee-peng LIU, Zhiwei ZHAO, Tianxiang |
author_facet |
WANG, Lei LIM, Ee-peng LIU, Zhiwei ZHAO, Tianxiang |
author_sort |
WANG, Lei |
title |
Explanation guided contrastive learning for sequential recommendation |
title_short |
Explanation guided contrastive learning for sequential recommendation |
title_full |
Explanation guided contrastive learning for sequential recommendation |
title_fullStr |
Explanation guided contrastive learning for sequential recommendation |
title_full_unstemmed |
Explanation guided contrastive learning for sequential recommendation |
title_sort |
explanation guided contrastive learning for sequential recommendation |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2022 |
url |
https://ink.library.smu.edu.sg/lkcsb_research/7084 https://ink.library.smu.edu.sg/context/lkcsb_research/article/8083/viewcontent/2209.01347.pdf |
_version_ |
1814047483437776896 |