CORE: Data Augmentation for Link Prediction via Information Bottleneck
This work addresses the generalizability issue in link prediction models for graph representation learning, which is incremental as it builds on existing methods with a novel augmentation approach.
The paper tackled the problem of link prediction in graphs by addressing noisy or spurious information and incomplete data, proposing the CORE data augmentation method based on the Information Bottleneck principle to recover missing edges and remove noise, resulting in enhanced robustness and performance as demonstrated in experiments on multiple benchmark datasets.
Link prediction (LP) is a fundamental task in graph representation learning, with numerous applications in diverse domains. However, the generalizability of LP models is often compromised due to the presence of noisy or spurious information in graphs and the inherent incompleteness of graph data. To address these challenges, we draw inspiration from the Information Bottleneck principle and propose a novel data augmentation method, COmplete and REduce (CORE) to learn compact and predictive augmentations for LP models. In particular, CORE aims to recover missing edges in graphs while simultaneously removing noise from the graph structures, thereby enhancing the model's robustness and performance. Extensive experiments on multiple benchmark datasets demonstrate the applicability and superiority of CORE over state-of-the-art methods, showcasing its potential as a leading approach for robust LP in graph representation learning.