arrow
返回

CollaborEM: A Self-Supervised Entity Matching Framework Using Multi-Features Collaboration

delete2023-12-01
delete1
delete
OA
AI
W
Wang, Pengfei
陈璐 封面图
陈璐 (Lu Chen)
X
Xiaoze Liu
B
Baihua Zheng
Y
Yunjun Gao *
DOI:10.1109/TKDE.2021.3134806delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
Entity Matching (EM) aims to identify whether two tuples refer to the same real-world entity and is well-known to be labor-intensive. It is a prerequisite to anomaly detection, as comparing the attribute values of two matched tuples from two different datasets provides one effective way to detect anomalies. Existing EM approaches, due to insufficient feature discovery or error-prone inherent characteristics, are not able to achieve stable performance. In this paper, we present CollaborEM, a self-supervised entity matching framework via multi-features collaboration. It is capable of (i) obtaining reliable EM results with zero human annotations and (ii) discovering adequate tuples' features in a fault-tolerant manner. CollaborEM consists of two phases, i.e., automatic label generation (ALG) and collaborative EM training (CEMT). In the first phase, ALG is proposed to generate a set of positive tuple pairs and a set of negative tuple pairs. ALG guarantees the high quality of the generated tuples, and hence ensures the training quality of the subsequent CEMT. In the second phase, CEMT is introduced to learn the matching signals by discovering graph features and sentence features of tuples collaboratively. Extensive experimental results over eight real-world EM benchmarks show that CollaborEM outperforms all the existing unsupervised EM approaches and is comparable or even superior to the state-of-the-art supervised EM methods.
Keyword:
Media
Collaboration
Anomaly detection
Feature extraction
Training
Task analysis
Semantics
Entity matching
sentence feature
graph feature
self-supervised
anomaly detection

期刊

IEEE Transactions on Knowledge and Data Engineering 封面图
IEEE Transactions on Knowledge and Data Engineering
IF:
10.4
论文数:
7.0K
被引数:
4.1W

机构

浙江大学 封面图
浙江大学
学者数:
561
论文数: 200
被引数: 9.6W
新
新加坡管理大学
学者数:
211
论文数: 151
被引数: 2.3K
引用论文

引用论文

Female directors and firm performance: Evidence from the Great Recession
err2019-07-01
err0
PREAI
errSuwongrat Papangkorn; Pattanaporn Chatjuthamard; Pornsit Jiraporn; Sirisak Chueykamhang
err分享
err收藏
err分享
err收藏
err分享
err收藏
Electron transfer by domain movement in cytochrome bc1
errNature
IF48.5
err1998-04-01
err0
PREAI
errZhaolei Zhang; Lishar Huang; Vladimir M. Shulmeister; Young-In Chi; Kyeong Kyu Kim; Li-Wei Hung; Antony R. Crofts; Edward A. Berry; Sung-Hou Kim
err分享
err收藏
Isokinetic assessment of knee flexors and extensors in professional soccer players
err2003-02-01
err0
errOAAI
errJ.L. Croisier; V. Reveillon; J.M. Ferret; T. Cotte; M. Genty; N. Popovich; Mohty Filho; J.E. Faryniuk; S. Ganteaume; J.M. Crielaard
err分享
err收藏
Epigallocatechin-3-gallate Increases Maximal Oxygen Uptake in Adult Humans
err2010-04-01
err0
errOAAI
errJENNIFER C. RICHARDS; MARK C. LONAC; TYLER K. JOHNSON; MELANI M. SCHWEDER; CHRISTOPHER BELL
err分享
err收藏
Analysis of Protein Oligomeric Species by Sucrose Gradients
err2016-09-10
err0
PREAI
errSandra Tenreiro; Diana Macedo; Zrinka Marijanovic; Tiago Fleming Outeiro
err分享
err收藏
学者 查看更多内容