MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler

10/17/2020
by   Zhining Liu, et al.
0

Imbalanced learning (IL), i.e., learning unbiased models from class-imbalanced data, is a challenging problem. Typical IL methods including resampling and reweighting were designed based on some heuristic assumptions. They often suffer from unstable performance, poor applicability, and high computational cost in complex tasks where their assumptions do not hold. In this paper, we introduce a novel ensemble IL framework named MESA. It adaptively resamples the training set in iterations to get multiple classifiers and forms a cascade ensemble model. MESA directly learns the sampling strategy from data to optimize the final metric beyond following random heuristics. Moreover, unlike prevailing meta-learning-based IL solutions, we decouple the model-training and meta-training in MESA by independently train the meta-sampler over task-agnostic meta-data. This makes MESA generally applicable to most of the existing learning models and the meta-sampler can be efficiently applied to new tasks. Extensive experiments on both synthetic and real-world tasks demonstrate the effectiveness, robustness, and transferability of MESA. Our code is available at https://github.com/ZhiningLiu1998/mesa.

READ FULL TEXT

page 6

page 13

08/24/2021

Adaptation-Agnostic Meta-Training

Many meta-learning algorithms can be formulated into an interleaved proc...
02/22/2021

MetaDelta: A Meta-Learning System for Few-shot Image Classification

Meta-learning aims at learning quickly on novel tasks with limited data ...
03/20/2021

MetaHDR: Model-Agnostic Meta-Learning for HDR Image Reconstruction

Capturing scenes with a high dynamic range is crucial to reproducing ima...
01/15/2021

Ensemble Learning Based Classification Algorithm Recommendation

Recommending appropriate algorithms to a classification problem is one o...
09/07/2021

Learning Fast Sample Re-weighting Without Reward Data

Training sample re-weighting is an effective approach for tackling data ...
09/29/2021

Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness

Recognizing new objects by learning from a few labeled examples in an ev...
08/12/2022

AutoShard: Automated Embedding Table Sharding for Recommender Systems

Embedding learning is an important technique in deep recommendation mode...