Counterfactual Generative Smoothing for Imbalanced Natural Language Classification

Hojae Han; Seungtaek Choi; Myeongho Jeong; Jin Woo Park; Seung Won Hwang

doi:10.1145/3459637.3482077

Counterfactual Generative Smoothing for Imbalanced Natural Language Classification

Hojae Han, Seungtaek Choi, Myeongho Jeong, Jin Woo Park, Seung Won Hwang

College of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

Classification datasets are often biased in observations, leaving onlya few observations for minority classes. Our key contribution is de-tecting and reducing Under-represented (U-) and Over-represented(O-) artifacts from dataset imbalance, by proposing a Counterfac-tual Generative Smoothing approach on both feature-space anddata-space, namely CGS_f and CGS_d. Our technical contribution issmoothing majority and minority observations, by sampling a ma-jority seed and transferring to minority. Our proposed approachesnot only outperform state-of-the-arts in both synthetic and real-lifedatasets, they effectively reduce both artifact types.

Original language	English
Title of host publication	CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management
Publisher	Association for Computing Machinery
Pages	3058-3062
Number of pages	5
ISBN (Electronic)	9781450384469
DOIs	https://doi.org/10.1145/3459637.3482077
Publication status	Published - 2021 Oct 26
Event	30th ACM International Conference on Information and Knowledge Management, CIKM 2021 - Virtual, Online, Australia Duration: 2021 Nov 1 → 2021 Nov 5

Publication series

Name	International Conference on Information and Knowledge Management, Proceedings

Conference

Conference	30th ACM International Conference on Information and Knowledge Management, CIKM 2021
Country/Territory	Australia
City	Virtual, Online
Period	21/11/1 → 21/11/5

Bibliographical note

Funding Information:
∗corresponding author, supported by Microsoft Research Asia and IITP grants (2021-0-01696, High-Potential Individuals Global Training Program, and 2021-0-01343, SNU AI Graduate School)

Publisher Copyright:
© 2021 ACM.

All Science Journal Classification (ASJC) codes

Business, Management and Accounting(all)
Decision Sciences(all)

Access to Document

10.1145/3459637.3482077

Cite this

Han, H., Choi, S., Jeong, M., Park, J. W., & Hwang, S. W. (2021). Counterfactual Generative Smoothing for Imbalanced Natural Language Classification. In CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management (pp. 3058-3062). (International Conference on Information and Knowledge Management, Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3459637.3482077

Han, Hojae ; Choi, Seungtaek ; Jeong, Myeongho et al. / Counterfactual Generative Smoothing for Imbalanced Natural Language Classification. CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2021. pp. 3058-3062 (International Conference on Information and Knowledge Management, Proceedings).

@inproceedings{53bb722d45b049cb960e23600050c00e,

title = "Counterfactual Generative Smoothing for Imbalanced Natural Language Classification",

abstract = "Classification datasets are often biased in observations, leaving onlya few observations for minority classes. Our key contribution is de-tecting and reducing Under-represented (U-) and Over-represented(O-) artifacts from dataset imbalance, by proposing a Counterfac-tual Generative Smoothing approach on both feature-space anddata-space, namely CGS_f and CGS_d. Our technical contribution issmoothing majority and minority observations, by sampling a ma-jority seed and transferring to minority. Our proposed approachesnot only outperform state-of-the-arts in both synthetic and real-lifedatasets, they effectively reduce both artifact types.",

author = "Hojae Han and Seungtaek Choi and Myeongho Jeong and Park, {Jin Woo} and Hwang, {Seung Won}",

note = "Funding Information: ∗corresponding author, supported by Microsoft Research Asia and IITP grants (2021-0-01696, High-Potential Individuals Global Training Program, and 2021-0-01343, SNU AI Graduate School) Publisher Copyright: {\textcopyright} 2021 ACM.; 30th ACM International Conference on Information and Knowledge Management, CIKM 2021 ; Conference date: 01-11-2021 Through 05-11-2021",

year = "2021",

month = oct,

day = "26",

doi = "10.1145/3459637.3482077",

language = "English",

series = "International Conference on Information and Knowledge Management, Proceedings",

publisher = "Association for Computing Machinery",

pages = "3058--3062",

booktitle = "CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management",

}

Han, H, Choi, S, Jeong, M, Park, JW & Hwang, SW 2021, Counterfactual Generative Smoothing for Imbalanced Natural Language Classification. in CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, Association for Computing Machinery, pp. 3058-3062, 30th ACM International Conference on Information and Knowledge Management, CIKM 2021, Virtual, Online, Australia, 21/11/1. https://doi.org/10.1145/3459637.3482077

Counterfactual Generative Smoothing for Imbalanced Natural Language Classification. / Han, Hojae; Choi, Seungtaek; Jeong, Myeongho et al.

CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2021. p. 3058-3062 (International Conference on Information and Knowledge Management, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Counterfactual Generative Smoothing for Imbalanced Natural Language Classification

AU - Han, Hojae

AU - Choi, Seungtaek

AU - Jeong, Myeongho

AU - Park, Jin Woo

AU - Hwang, Seung Won

N1 - Funding Information: ∗corresponding author, supported by Microsoft Research Asia and IITP grants (2021-0-01696, High-Potential Individuals Global Training Program, and 2021-0-01343, SNU AI Graduate School) Publisher Copyright: © 2021 ACM.

PY - 2021/10/26

Y1 - 2021/10/26

N2 - Classification datasets are often biased in observations, leaving onlya few observations for minority classes. Our key contribution is de-tecting and reducing Under-represented (U-) and Over-represented(O-) artifacts from dataset imbalance, by proposing a Counterfac-tual Generative Smoothing approach on both feature-space anddata-space, namely CGS_f and CGS_d. Our technical contribution issmoothing majority and minority observations, by sampling a ma-jority seed and transferring to minority. Our proposed approachesnot only outperform state-of-the-arts in both synthetic and real-lifedatasets, they effectively reduce both artifact types.

AB - Classification datasets are often biased in observations, leaving onlya few observations for minority classes. Our key contribution is de-tecting and reducing Under-represented (U-) and Over-represented(O-) artifacts from dataset imbalance, by proposing a Counterfac-tual Generative Smoothing approach on both feature-space anddata-space, namely CGS_f and CGS_d. Our technical contribution issmoothing majority and minority observations, by sampling a ma-jority seed and transferring to minority. Our proposed approachesnot only outperform state-of-the-arts in both synthetic and real-lifedatasets, they effectively reduce both artifact types.

UR - http://www.scopus.com/inward/record.url?scp=85119204445&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85119204445&partnerID=8YFLogxK

U2 - 10.1145/3459637.3482077

DO - 10.1145/3459637.3482077

M3 - Conference contribution

AN - SCOPUS:85119204445

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 3058

EP - 3062

BT - CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management

PB - Association for Computing Machinery

T2 - 30th ACM International Conference on Information and Knowledge Management, CIKM 2021

Y2 - 1 November 2021 through 5 November 2021

ER -

Han H, Choi S, Jeong M, Park JW, Hwang SW. Counterfactual Generative Smoothing for Imbalanced Natural Language Classification. In CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2021. p. 3058-3062. (International Conference on Information and Knowledge Management, Proceedings). doi: 10.1145/3459637.3482077

Counterfactual Generative Smoothing for Imbalanced Natural Language Classification

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this