GraphSAGE++: Weighted Multi-scale GNN for Graph Representation Learning

Abstract

Graph neural networks (GNNs) have emerged as a powerful tool in graph representation learning. However, they are increasingly challenged by over-smoothing as network depth grows, compromising their ability to capture and represent complex graph structures. Additionally, some popular GNN variants only consider local neighbor information during node updating, ignoring the global structural information and leading to inadequate learning and differentiation of graph structures. To address these challenges, we introduce a novel graph neural network framework, GraphSAGE++. Our model extracts the representation of the target node at each layer and then concatenates all layer weighted representations to obtain the final result. In addition, the strategies combining double aggregations with weighted concatenation are proposed, which significantly enhance the model’s discernment and preservation of structural information. Empirical results on various datasets demonstrate that GraphSAGE++ excels in vertex classification, link prediction, and visualization tasks, surpassing existing methods in effectiveness.

Link Prediction in Dynamic Social Networks Combining Entropy, Causality, and a Graph Convolutional Network Model

“…Recently, some researchers have proposed several hybrid models for link prediction to improve its performance [ 21 ]. Jiawei et al [ 22 ] proposed a new graph neural network framework, GraphSAGE++, which introduced causal inference into the GraphSAGE model and used aggregation functions to integrate selected neighbor features into the feature vector generation of target nodes. Tan et al [ 23 ] proposed a counterfactual and factual (CF2) reasoning-based deep neural network interpretation and evaluation method for graph prediction.…”