Timezone: »

 
Poster
LOG: Active Model Adaptation for Label-Efficient OOD Generalization
Jie-Jing Shao · Lan-Zhe Guo · Xiao-wen Yang · Yu-Feng Li

@

This work discusses how to achieve worst-case Out-Of-Distribution (OOD) generalization for a variety of distributions based on a relatively small labeling cost. The problem has broad applications, especially in non-i.i.d. open-world scenarios. Previous studies either rely on a large amount of labeling cost or lack of guarantees about the worst-case generalization. In this work, we show for the first time that active model adaptation could achieve both good performance and robustness based on the invariant risk minimization principle. We propose \textsc{Log}, an interactive model adaptation framework, with two sub-modules: active sample selection and causal invariant learning. Specifically, we formulate the active selection as a mixture distribution separation problem and present an unbiased estimator, which could find the samples that violate the current invariant relationship, with a provable guarantee. The theoretical analysis supports that both sub-modules contribute to generalization. A large number of experimental results confirm the promising performance of the new algorithm.

Author Information

Jie-Jing Shao (Nanjing University)
Lan-Zhe Guo (Nanjing University)
Xiao-wen Yang (Nanjing University)
Yu-Feng Li (Nanjing University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors

  • 2022 Poster: Robust Semi-Supervised Learning when Not All Classes have Labels »
    Lan-Zhe Guo · Yi-Ge Zhang · Zhi-Fan Wu · Jie-Jing Shao · Yu-Feng Li
  • 2022 Spotlight: Lightning Talks 3A-2 »
    shuwen yang · Xu Zhang · Delvin Ce Zhang · Lan-Zhe Guo · Renzhe Xu · Zhuoer Xu · Yao-Xiang Ding · Weihan Li · Xingxuan Zhang · Xi-Zhu Wu · Zhenyuan Yuan · Hady Lauw · Yu Qi · Yi-Ge Zhang · Zhihao Yang · Guanghui Zhu · Dong Li · Changhua Meng · Kun Zhou · Gang Pan · Zhi-Fan Wu · Bo Li · Minghui Zhu · Zhi-Hua Zhou · Yafeng Zhang · Yingxueff Zhang · shiwen cui · Jie-Jing Shao · Zhanguang Zhang · Zhenzhe Ying · Xiaolong Chen · Yu-Feng Li · Guojie Song · Peng Cui · Weiqiang Wang · Ming GU · Jianye Hao · Yihua Huang
  • 2022 Spotlight: Robust Semi-Supervised Learning when Not All Classes have Labels »
    Lan-Zhe Guo · Yi-Ge Zhang · Zhi-Fan Wu · Jie-Jing Shao · Yu-Feng Li
  • 2022 Spotlight: Lightning Talks 2B-3 »
    Jie-Jing Shao · Jiangmeng Li · Jiashuo Liu · Zongbo Han · Tianyang Hu · Jiayun Wu · Wenwen Qiang · Jun WANG · Zhipeng Liang · Lan-Zhe Guo · Wenjia Wang · Yanan Zhang · Xiao-wen Yang · Fan Yang · Bo Li · Wenyi Mo · Zhenguo Li · Liu Liu · Peng Cui · Yu-Feng Li · Changwen Zheng · Lanqing Li · Yatao Bian · Bing Su · Hui Xiong · Peilin Zhao · Bingzhe Wu · Changqing Zhang · Jianhua Yao
  • 2022 Poster: USB: A Unified Semi-supervised Learning Benchmark for Classification »
    Yidong Wang · Hao Chen · Yue Fan · Wang SUN · Ran Tao · Wenxin Hou · Renjie Wang · Linyi Yang · Zhi Zhou · Lan-Zhe Guo · Heli Qi · Zhen Wu · Yu-Feng Li · Satoshi Nakamura · Wei Ye · Marios Savvides · Bhiksha Raj · Takahiro Shinozaki · Bernt Schiele · Jindong Wang · Xing Xie · Yue Zhang
  • 2021 Poster: STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data »
    Zhi Zhou · Lan-Zhe Guo · Zhanzhan Cheng · Yu-Feng Li · Shiliang Pu