Timezone: »

Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile
Dong Chen · Lingfei Wu · Siliang Tang · Xiao Yun · Bo Long · Yueting Zhuang

Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #521

Recent years have seen a surge of interest in meta-learning techniques for tackling the few-shot learning (FSL) problem. However, the meta-learner is prone to overfitting since there are only a few available samples, which can be identified as sampling noise on a clean dataset. Besides, when handling the data with noisy labels, the meta-learner could be extremely sensitive to label noise on a corrupted dataset. To address these two challenges, we present Eigen-Reptile (ER) that updates the meta-parameters with the main direction of historical task-specific parameters. Specifically, the main direction is computed in a fast way, where the scale of the calculated matrix is related to the number of gradient steps for the specific task instead of the number of parameters. Furthermore, to obtain a more accurate main direction for Eigen-Reptile in the presence of many noisy labels, we further propose Introspective Self-paced Learning (ISPL). We have theoretically and experimentally demonstrated the soundness and effectiveness of the proposed Eigen-Reptile and ISPL. Particularly, our experiments on different tasks show that the proposed method is able to outperform or achieve highly competitive performance compared with other gradient-based methods with or without noisy labels. The code and data for the proposed method are provided for research purposes https://github.com/Anfeather/Eigen-Reptile.

Author Information

Dong Chen (Zhejiang University)
Lingfei Wu (JD.COM Silicon Valley Research Center)
Siliang Tang (Zhejiang University)
Xiao Yun (JD.com)
Bo Long (JD.com)
Yueting Zhuang (Zhejiang University)

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

More from the Same Authors