Adversarial Training with Complementary Labels: On the Necessity of Gradually Informative Attacks

Jianan Zhou, Jianing Zhu, Jingfeng Zhang, Tongliang Liu, Gang Niu*, Bo Han*, Masashi Sugiyama

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Adversarial training (AT) with imperfect supervision is significant but receives limited attention. To push AT towards more practical scenarios, we explore a brand new yet challenging setting, i.e., AT with complementary labels (CLs), which specify a class that a data sample does not belong to. However, the direct combination of AT with existing methods for CLs results in consistent failure, but not on a simple baseline of two-stage training. In this paper, we further explore the phenomenon and identify the underlying challenges of AT with CLs as intractable adversarial optimization and low-quality adversarial examples. To address the above problems, we propose a new learning strategy using gradually informative attacks, which consists of two critical components: 1) Warm-up Attack (Warm-up) gently raises the adversarial perturbation budgets to ease the adversarial optimization with CLs; 2) Pseudo-Label Attack (PLA) incorporates the progressively informative model predictions into a corrected complementary loss. Extensive experiments are conducted to demonstrate the effectiveness of our method on a range of benchmarked datasets. The code is publicly available at: https://github.com/RoyalSkye/ATCL.
Original languageEnglish
Title of host publication36th Conference on Neural Information Processing Systems (NeurIPS 2022)
PublisherNeural Information Processing Systems Foundation
Pages1-13
Number of pages13
Publication statusPublished - Nov 2022
Event36th Conference on Neural Information Processing Systems, NeurIPS 2022 - New Orleans Convention Center, New Orleans, United States
Duration: 28 Nov 20229 Dec 2022
https://neurips.cc/Conferences/2022
https://openreview.net/group?id=NeurIPS.cc/2022/Conference
https://proceedings.neurips.cc/paper_files/paper/2022

Publication series

NameAdvances in Neural Information Processing Systems
Volume35
ISSN (Print)1049-5258
NameNeurIPS Proceedings

Conference

Conference36th Conference on Neural Information Processing Systems, NeurIPS 2022
Country/TerritoryUnited States
CityNew Orleans
Period28/11/229/12/22
Internet address

Fingerprint

Dive into the research topics of 'Adversarial Training with Complementary Labels: On the Necessity of Gradually Informative Attacks'. Together they form a unique fingerprint.

Cite this