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
秋天爱吃板栗应助求助采纳,获得50
刚刚
所所应助qishi采纳,获得10
1秒前
我是老大应助naturehome采纳,获得10
3秒前
3秒前
Ly发布了新的文献求助10
3秒前
大个应助张小龙采纳,获得10
4秒前
猫南北完成签到,获得积分10
5秒前
5秒前
5秒前
5秒前
西屿发布了新的文献求助10
7秒前
7秒前
海藻发布了新的文献求助10
7秒前
dodo完成签到 ,获得积分10
8秒前
硕shuo完成签到 ,获得积分10
9秒前
Jasper应助andy-law采纳,获得10
9秒前
Hello应助Sievi采纳,获得10
9秒前
carryxxx关注了科研通微信公众号
9秒前
10秒前
10秒前
聪明天佑完成签到 ,获得积分10
10秒前
TheForest发布了新的文献求助20
12秒前
12秒前
Simon发布了新的文献求助10
12秒前
12秒前
naturehome发布了新的文献求助10
14秒前
Akim应助杰瑞采纳,获得10
14秒前
14秒前
可爱的函函应助ZC采纳,获得10
14秒前
科研通AI2S应助成就紫真采纳,获得10
15秒前
一只小方块完成签到,获得积分10
15秒前
勇敢的前进完成签到,获得积分10
16秒前
泊頔发布了新的文献求助10
17秒前
18秒前
小瓦片完成签到,获得积分10
18秒前
18秒前
科研通AI2S应助Muxi采纳,获得10
19秒前
木木完成签到 ,获得积分10
19秒前
19秒前
20秒前
高分求助中
Sustainability in Tides Chemistry 2000
The ACS Guide to Scholarly Communication 2000
Studien zur Ideengeschichte der Gesetzgebung 1000
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Threaded Harmony: A Sustainable Approach to Fashion 810
Pharmacogenomics: Applications to Patient Care, Third Edition 800
Gerard de Lairesse : an artist between stage and studio 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 3076461
求助须知:如何正确求助?哪些是违规求助? 2729295
关于积分的说明 7508443
捐赠科研通 2377577
什么是DOI,文献DOI怎么找? 1260686
科研通“疑难数据库(出版商)”最低求助积分说明 611122
版权声明 597203