Adapt, Agree, Aggregate: Semi-Supervised Ensemble Labeling for Graph Convolutional Networks
This work addresses challenges in graph-based semi-supervised learning for applications like social network analysis or recommendation systems, but it appears incremental as it builds on existing ensemble and augmentation techniques.
The paper tackles the problem of semi-supervised node classification in graphs by proposing a framework that combines ensemble learning with augmented graph structures, resulting in improved performance and robustness as demonstrated on real-world datasets.
In this paper, we propose a novel framework that combines ensemble learning with augmented graph structures to improve the performance and robustness of semi-supervised node classification in graphs. By creating multiple augmented views of the same graph, our approach harnesses the "wisdom of a diverse crowd", mitigating the challenges posed by noisy graph structures. Leveraging ensemble learning allows us to simultaneously achieve three key goals: adaptive confidence threshold selection based on model agreement, dynamic determination of the number of high-confidence samples for training, and robust extraction of pseudo-labels to mitigate confirmation bias. Our approach uniquely integrates adaptive ensemble consensus to flexibly guide pseudo-label extraction and sample selection, reducing the risks of error accumulation and improving robustness. Furthermore, the use of ensemble-driven consensus for pseudo-labeling captures subtle patterns that individual models often overlook, enabling the model to generalize better. Experiments on several real-world datasets demonstrate the effectiveness of our proposed method.