We are happy to announce that we have a full paper accepted by CCF-A conference ICDE 2020!
Zhining Liu is the first author of this paper. He is a 1st-year M.S. candidate at the School of AI, Jilin University. He was supervised by Prof. Yi Chang.
This work was done in collaboration with researchers at Microsoft Research Asia (MSRA). They are Dr. Wei Cao (Associate Researcher), Dr. Jiang Bian (Lead Researcher) and Dr. Tie-yan Liu (Assistant Managing Director of MSRA).
Title: Self-paced Ensemble for Highly Imbalanced Massive Data Classification
Conference: IEEE International Conference on Data Engineering (ICDE) 2020
Time & Venue: April 20th-24th, 2020, Dallas, Texas, USA
Abstract: Many real-world applications reveal difficulties in learning classifiers from imbalanced data. The rising big data era has been witnessing more classification tasks with largescale but extremely imbalance and low-quality datasets. Most of existing learning methods suffer from poor performance or low computation efficiency under such a scenario. To tackle this problem, we conduct deep investigations into the nature of class imbalance, which reveals that not only the disproportion between classes, but also other difficulties embedded in the nature of data, especially, noises and class overlapping, prevent us from learning effective classifiers. Taking those factors into consideration, we propose a novel framework for imbalance classification that aims to generate a strong ensemble by self-paced harmonizing data hardness via under-sampling. Extensive experiments have shown that this new framework, while being very computationally efficient, can lead to robust performance even under highly overlapping classes and extremely skewed distribution. Note that, our methods can be easily adapted to most of existing learning methods (e.g., C4.5, SVM, GBDT and Neural Network) to boost their performance on imbalanced data.