2021/07/06 by Huafeng Yang, Qijie Shen, Yang, Huafeng +7
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #HIV, Drug Use, Sexual Risk #Imbalanced Data Classification Techniques #cs.CV
paper · pdf · doi:10.48550/arxiv.2107.02477
9 pages, accepted by SIAM International Conference on Data Mining (SDM) 2023
openalex publication_date 2021/07/06 · arxiv created 2022/12/29 · arxiv updated 2023/01/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In recent years, benefiting from the expressive power of Graph Convolutional Networks (GCNs), significant breakthroughs have been made in face clustering area. However, rare attention has been paid to GCN-based clustering on imbalanced data. Although imbalance problem has been extensively studied, the impact of imbalanced data on GCN- based linkage prediction task is quite different, which would cause problems in two aspects: imbalanced linkage labels and biased graph representations. The former is similar to that in classic image classification task, but the latter is a particular problem in GCN-based clustering via linkage prediction. Significantly biased graph representations in training can cause catastrophic over-fitting of a GCN model. To tackle these challenges, we propose a linkage-based doubly imbalanced graph learning framework for face clustering. In this framework, we evaluate the feasibility of those existing methods for imbalanced image classification problem on GCNs, and present a new method to alleviate the imbalanced labels and also augment graph representations using a Reverse-Imbalance Weighted Sampling (RIWS) strategy. With the RIWS strategy, probability-based class balancing weights could ensure the overall distribution of positive and negative samples; in addition, weighted random sampling provides diverse subgraph structures, which effectively alleviates the over-fitting problem and improves the representation ability of GCNs. Extensive experiments on series of imbalanced benchmark datasets synthesized from MS-Celeb-1M and DeepFashion demonstrate the effectiveness and generality of our proposed method. Our implementation and the synthesized datasets will be openly available on https://github.com/espectre/GCNsonimbalanceddatasets.