MSSM: A Multiple-level Sparse Sharing Model for Efficient Multi-Task Learning

计算机科学 多任务学习 任务(项目管理) 人工智能 机器学习 学习迁移 集合(抽象数据类型) 领域(数学) 特征(语言学) 一般化 程序设计语言 数学 语言学 数学分析 哲学 经济 管理 纯数学
作者
Ke Ding,Xin Dong,Yong He,Lei Cheng,Chilin Fu,Zhaoxin Huan,Hai Li,Tan Yan,Liang Zhang,Xiaolu Zhang,Linjian Mo
标识
DOI:10.1145/3404835.3463022
摘要

Multi-task learning(MTL) is an open and challenging problem in various real-world applications. The typical way of conducting multi-task learning is establishing some global parameter sharing mechanism across all tasks or assigning each task an individual set of parameters with cross-connections between tasks. However, for most existing approaches, all tasks just thoroughly or proportionally share all the features without distinguishing the helpfulness of them. By that, some tasks would be intervened by the unhelpful features that are useful for other tasks, leading to undesired negative transfer between tasks. In this paper, we design a novel architecture named the Multiple-level Sparse Sharing Model (MSSM), which can learn features selectively and share knowledge across all tasks efficiently. MSSM first employs a field-level sparse connection module (FSCM) to enable much more expressive combinations of feature fields to be learned for generalization across tasks while still allowing for task-specific features to be customized for each task. Furthermore, a cell-level sparse sharing module (CSSM) can recognize the sharing pattern through a set of coding variables that selectively choose which cells to route for a given task. Extensive experimental results on several real-world datasets show that MSSM outperforms SOTA models significantly in terms of AUC and LogLoss metrics.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
刚刚
Hollow发布了新的文献求助10
刚刚
2秒前
常琳琳发布了新的文献求助10
2秒前
2秒前
LL完成签到,获得积分10
2秒前
深情安青应助slx采纳,获得10
2秒前
3秒前
3秒前
如意枫叶发布了新的文献求助10
3秒前
FashionBoy应助03采纳,获得10
5秒前
5秒前
幸福大白发布了新的文献求助30
5秒前
充电宝应助展希希采纳,获得10
7秒前
诚心谷南发布了新的文献求助10
8秒前
舒服的元瑶完成签到 ,获得积分10
8秒前
MEDwhy发布了新的文献求助10
9秒前
9秒前
10秒前
10秒前
雨天完成签到,获得积分10
10秒前
思源应助一支布洛芬采纳,获得10
11秒前
11秒前
璀璨完成签到,获得积分10
15秒前
JamesPei应助虚幻秋白采纳,获得10
15秒前
YJ888发布了新的文献求助10
16秒前
思源应助Hollow采纳,获得10
17秒前
17秒前
17秒前
盐植物完成签到,获得积分10
17秒前
18秒前
evans完成签到,获得积分10
19秒前
sanwan完成签到,获得积分10
20秒前
李健的小迷弟应助橙子采纳,获得10
22秒前
22秒前
23秒前
23秒前
孟德尔的豌豆完成签到,获得积分20
24秒前
yw11发布了新的文献求助10
24秒前
25秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989550
求助须知:如何正确求助?哪些是违规求助? 3531774
关于积分的说明 11254747
捐赠科研通 3270278
什么是DOI,文献DOI怎么找? 1804966
邀请新用户注册赠送积分活动 882125
科研通“疑难数据库(出版商)”最低求助积分说明 809176