Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily

Abstract

Graph Neural Networks (GNNs) show strong expressive power on graph data mining, by aggregating information from neighbors and using the integrated representation in the downstream tasks. The same aggregation methods and parameters for each node in a graph are used to enable the GNNs to utilize the homophily relational data. However, not all graphs are homophilic, even in the same graph, the distributions may vary significantly. Using the same convolution over all nodes may lead to the ignorance of various graph patterns. Furthermore, many existing GNNs integrate node features and structure identically, which ignores the distributions of nodes and further limits the expressive power of GNNs. To solve these problems, we propose Meta Weight Graph Neural Network (MWGNN) to adaptively construct graph convolution layers for different nodes. First, we model the Node Local Distribution (NLD) from node feature, topological structure and positional identity aspects with the Meta-Weight. Then, based on the Meta-Weight, we generate the adaptive graph convolutions to perform a node-specific weighted aggregation and boost the node representations. Finally, we design extensive experiments on real-world and synthetic benchmarks to evaluate the effectiveness of MWGNN. These experiments show the excellent expressive power of MWGNN in dealing with graph data with various distributions.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Statistical mechanics of complex networks
• Spectral Networks and Locally Connected Networks on Graphs
• Simplifying Graph Convolutional Networks
• struc2vec: Learning Node Representations from Structural Identity
• Towards Deeper Graph Neural Networks
• AM-GCN: Adaptive Multi-channel Graph Convolutional Networks
• Predict then Propagate: Graph Neural Networks meet Personalized PageRank
• Simple and Deep Graph Convolutional Networks
• Do Transformers Really Perform Bad for Graph Representation?
• DAG-GNN: DAG Structure Learning with Graph Neural Networks
• A simple yet effective baseline for non-attributed graph classification

Cited by in corpus (6)

• Continual Learning on Dynamic Graphs via Parameter Isolation
• Homophily-oriented Heterogeneous Graph Rewiring
• Graph Neural Networks with Diverse Spectral Filtering
• MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution
• ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting
• DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach