تقرير
Effective Eigendecomposition based Graph Adaptation for Heterophilic Networks
| العنوان: | Effective Eigendecomposition based Graph Adaptation for Heterophilic Networks |
|---|---|
| المؤلفون: | Lingam, Vijay, Ragesh, Rahul, Iyer, Arun, Sellamanickam, Sundararajan |
| سنة النشر: | 2021 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Social and Information Networks |
| الوصف: | Graph Neural Networks (GNNs) exhibit excellent performance when graphs have strong homophily property, i.e. connected nodes have the same labels. However, they perform poorly on heterophilic graphs. Several approaches address the issue of heterophily by proposing models that adapt the graph by optimizing task-specific loss function using labelled data. These adaptations are made either via attention or by attenuating or enhancing various low-frequency/high-frequency signals, as needed for the task at hand. More recent approaches adapt the eigenvalues of the graph. One important interpretation of this adaptation is that these models select/weigh the eigenvectors of the graph. Based on this interpretation, we present an eigendecomposition based approach and propose EigenNetwork models that improve the performance of GNNs on heterophilic graphs. Performance improvement is achieved by learning flexible graph adaptation functions that modulate the eigenvalues of the graph. Regularization of these functions via parameter sharing helps to improve the performance even more. Our approach achieves up to 11% improvement in performance over the state-of-the-art methods on heterophilic graphs. Comment: arXiv admin note: text overlap with arXiv:2106.12807 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2107.13312 |
| رقم الأكسشن: | edsarx.2107.13312 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |