Attention Calibration for Transformer-based Sequential Recommendation

计算机科学 变压器 水准点(测量) 人工智能 机器学习 数据挖掘 工程类 大地测量学 电压 地理 电气工程
作者
Peilin Zhou,Qichen Ye,Yueqi Xie,Joy Gao,Shoujin Wang,Jae Boum Kim,Chenyu You,Sung Hun Kim
标识
DOI:10.1145/3583780.3614785
摘要

Transformer-based sequential recommendation (SR) has been booming in recent years, with the self-attention mechanism as its key component. Self-attention has been widely believed to be able to effectively select those informative and relevant items from a sequence of interacted items for next-item prediction via learning larger attention weights for these items. However, this may not always be true in reality. Our empirical analysis of some representative Transformer-based SR models reveals that it is not uncommon for large attention weights to be assigned to less relevant items, which can result in inaccurate recommendations. Through further in-depth analysis, we find two factors that may contribute to such inaccurate assignment of attention weights:sub-optimal position encoding andnoisy input. To this end, in this paper, we aim to address this significant yet challenging gap in existing works. To be specific, we propose a simple yet effective framework called Attention Calibration for Transformer-based Sequential Recommendation (AC-TSR). In AC-TSR, a novel spatial calibrator and adversarial calibrator are designed respectively to directly calibrates those incorrectly assigned attention weights. The former is devised to explicitly capture the spatial relationships (i.e., order and distance) among items for more precise calculation of attention weights. The latter aims to redistribute the attention weights based on each item's contribution to the next-item prediction. AC-TSR is readily adaptable and can be seamlessly integrated into various existing transformer-based SR models. Extensive experimental results on four benchmark real-world datasets demonstrate the superiority of our proposed AC-TSR via significant recommendation performance enhancements. The source code is available at https://github.com/AIM-SE/AC-TSR.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
胡英俊发布了新的文献求助10
刚刚
刚刚
刚刚
C居完成签到 ,获得积分10
1秒前
幽默的千秋完成签到 ,获得积分10
1秒前
脑洞疼应助白文博采纳,获得10
1秒前
幌子完成签到 ,获得积分10
1秒前
2秒前
2秒前
MET1完成签到,获得积分10
2秒前
上进生完成签到,获得积分10
2秒前
yagami发布了新的文献求助10
2秒前
3秒前
3秒前
shmorby完成签到 ,获得积分10
4秒前
langwang完成签到,获得积分10
5秒前
5秒前
5秒前
quhayley完成签到,获得积分0
6秒前
lijuan发布了新的文献求助10
6秒前
6秒前
6秒前
科研文献搬运工应助liniubi采纳,获得30
8秒前
慕容半邪发布了新的文献求助10
8秒前
9秒前
9秒前
张沐发布了新的文献求助10
9秒前
9秒前
Windy完成签到,获得积分10
9秒前
wynn完成签到,获得积分10
10秒前
被动科研完成签到,获得积分10
10秒前
地西泮发布了新的文献求助10
11秒前
11秒前
12秒前
今后应助C居采纳,获得30
13秒前
学术小白完成签到,获得积分10
13秒前
13秒前
13秒前
呜啦啦发布了新的文献求助10
13秒前
sy完成签到 ,获得积分10
14秒前
高分求助中
Evolution 10000
Sustainability in Tides Chemistry 2800
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
юрские динозавры восточного забайкалья 800
A new approach of magnetic circular dichroism to the electronic state analysis of intact photosynthetic pigments 500
Diagnostic immunohistochemistry : theranostic and genomic applications 6th Edition 500
Chen Hansheng: China’s Last Romantic Revolutionary 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3148786
求助须知:如何正确求助?哪些是违规求助? 2799787
关于积分的说明 7837076
捐赠科研通 2457292
什么是DOI,文献DOI怎么找? 1307821
科研通“疑难数据库(出版商)”最低求助积分说明 628276
版权声明 601663