Abstract

Another challenge for mobile data mining tasks is personalization. On one hand, we usually do not have plenty labels for a certain user, and thus we need to borrow the labeled data from other users. One the other hand, different users tend to behavior differently and thus have different patterns of sensor readings, making data borrowing non-trivial. In this chapter, we introduce a personalized treatment for mobile data mining tasks. The basic idea can be divided into two stages. In the first stage, for a given target user, we select and borrow some data from the users whose labeled data are already collected in the database. In the second stage, we reweight the borrowed data and use them as the training data for the target user. The proposed method is able to estimate the sample distributions, and then reweight the samples based on the estimated distributions so as to minimize the model loss with respect to the target user’s data.

Original languageEnglish (US)
Title of host publicationSpringerBriefs in Computer Science
PublisherSpringer
Pages31-41
Number of pages11
DOIs
StatePublished - Jan 1 2018

Publication series

NameSpringerBriefs in Computer Science
ISSN (Print)2191-5768
ISSN (Electronic)2191-5776

Fingerprint

Data mining
Labels
Sensors

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Yao, Y., Su, X., & Tong, H. (2018). Personalized Model. In SpringerBriefs in Computer Science (pp. 31-41). (SpringerBriefs in Computer Science). Springer. https://doi.org/10.1007/978-3-030-02101-6_5

Personalized Model. / Yao, Yuan; Su, Xing; Tong, Hanghang.

SpringerBriefs in Computer Science. Springer, 2018. p. 31-41 (SpringerBriefs in Computer Science).

Research output: Chapter in Book/Report/Conference proceedingChapter

Yao, Y, Su, X & Tong, H 2018, Personalized Model. in SpringerBriefs in Computer Science. SpringerBriefs in Computer Science, Springer, pp. 31-41. https://doi.org/10.1007/978-3-030-02101-6_5
Yao Y, Su X, Tong H. Personalized Model. In SpringerBriefs in Computer Science. Springer. 2018. p. 31-41. (SpringerBriefs in Computer Science). https://doi.org/10.1007/978-3-030-02101-6_5
Yao, Yuan ; Su, Xing ; Tong, Hanghang. / Personalized Model. SpringerBriefs in Computer Science. Springer, 2018. pp. 31-41 (SpringerBriefs in Computer Science).
@inbook{985f48b1a79745a1a6cd2f6de4b94b41,
title = "Personalized Model",
abstract = "Another challenge for mobile data mining tasks is personalization. On one hand, we usually do not have plenty labels for a certain user, and thus we need to borrow the labeled data from other users. One the other hand, different users tend to behavior differently and thus have different patterns of sensor readings, making data borrowing non-trivial. In this chapter, we introduce a personalized treatment for mobile data mining tasks. The basic idea can be divided into two stages. In the first stage, for a given target user, we select and borrow some data from the users whose labeled data are already collected in the database. In the second stage, we reweight the borrowed data and use them as the training data for the target user. The proposed method is able to estimate the sample distributions, and then reweight the samples based on the estimated distributions so as to minimize the model loss with respect to the target user’s data.",
author = "Yuan Yao and Xing Su and Hanghang Tong",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-3-030-02101-6_5",
language = "English (US)",
series = "SpringerBriefs in Computer Science",
publisher = "Springer",
pages = "31--41",
booktitle = "SpringerBriefs in Computer Science",

}

TY - CHAP

T1 - Personalized Model

AU - Yao, Yuan

AU - Su, Xing

AU - Tong, Hanghang

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Another challenge for mobile data mining tasks is personalization. On one hand, we usually do not have plenty labels for a certain user, and thus we need to borrow the labeled data from other users. One the other hand, different users tend to behavior differently and thus have different patterns of sensor readings, making data borrowing non-trivial. In this chapter, we introduce a personalized treatment for mobile data mining tasks. The basic idea can be divided into two stages. In the first stage, for a given target user, we select and borrow some data from the users whose labeled data are already collected in the database. In the second stage, we reweight the borrowed data and use them as the training data for the target user. The proposed method is able to estimate the sample distributions, and then reweight the samples based on the estimated distributions so as to minimize the model loss with respect to the target user’s data.

AB - Another challenge for mobile data mining tasks is personalization. On one hand, we usually do not have plenty labels for a certain user, and thus we need to borrow the labeled data from other users. One the other hand, different users tend to behavior differently and thus have different patterns of sensor readings, making data borrowing non-trivial. In this chapter, we introduce a personalized treatment for mobile data mining tasks. The basic idea can be divided into two stages. In the first stage, for a given target user, we select and borrow some data from the users whose labeled data are already collected in the database. In the second stage, we reweight the borrowed data and use them as the training data for the target user. The proposed method is able to estimate the sample distributions, and then reweight the samples based on the estimated distributions so as to minimize the model loss with respect to the target user’s data.

UR - http://www.scopus.com/inward/record.url?scp=85056583250&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056583250&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-02101-6_5

DO - 10.1007/978-3-030-02101-6_5

M3 - Chapter

AN - SCOPUS:85056583250

T3 - SpringerBriefs in Computer Science

SP - 31

EP - 41

BT - SpringerBriefs in Computer Science

PB - Springer

ER -