Enhanced Graph Neural Networks with Ego-Centric Spectral Subgraph Embeddings Augmentation

• Published in: 2023 International Conference on Machine Learning and Applications (ICMLA) pp. 2257 - 2264
• Main Authors: Said, Anwar, Shabbir, Mudassir, Derr, Tyler, Abbas, Waseem, Koutsoukos, Xenofon
• Format: Conference Proceeding
• Language: English
• Published: IEEE 15.12.2023
• Subjects: Abnormal Features; Complex networks; Feature extraction; Graph Descriptors; Graph Neural Networks; Limiting; Machine learning; Message passing; Organizations; Social networking (online); Subgraph Spectral Embeddings
• ISSN: 1946-0759
• DOI: 10.1109/ICMLA58977.2023.00341

Graph Neural Networks (GNNs) have shown remarkable merit in performing various learning-based tasks in complex networks. The superior performance of GNNs often correlates with the availability and quality of node-level features in the input networks. However, for many network applications, such node-level information may be missing or unreliable, thereby limiting the applicability and efficacy of GNNs. To address this limitation, we present a novel approach denoted as Ego-centric Spectral subGraph Embedding Augmentation (ESGEA), which aims to enhance and design node features, particularly in scenarios where information is lacking. Our method leverages the topological structure of the local subgraph to create topology-aware node features. The subgraph features are generated using an efficient spectral graph embedding technique, and they serve as node features that capture the local topological organization of the network. The explicit node features, if present, are then enhanced with the subgraph embeddings in order to improve the overall performance. ESGEA is compatible with any GNN-based architecture and is effective even in the absence of node features. We evaluate the proposed method in a social network graph classification task where node attributes are unavailable, as well as in a node classification task where node features are corrupted or even absent. The evaluation results on seven datasets and eight baseline models indicate up to a 10% improvement in AUC and a 7% improvement in accuracy for graph and node classification tasks, respectively.