Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs

Abstract

Graph neural networks (GNNs) have been extensively studied for prediction tasks on graphs. As pointed out by recent studies, most GNNs assume local homophily, i.e., strong similarities in local neighborhoods. This assumption however limits the generalizability power of GNNs. To address this limitation, we propose a flexible GNN model, which is capable of handling any graphs without being restricted by their underlying homophily. At its core, this model adopts a node attention mechanism based on multiple learnable spectral filters; therefore, the aggregation scheme is learned adaptively for each graph in the spectral domain. We evaluated the proposed model on node classification tasks over eight benchmark datasets. The proposed model is shown to generalize well to both homophilic and heterophilic graphs. Further, it outperforms all state-of-the-art baselines on heterophilic graphs and performs comparably with them on homophilic graphs.

arXiv comment17 pages, 5 figures,conference

References in corpus (21)

• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• Fast Graph Representation Learning with PyTorch Geometric
• struc2vec: Learning Node Representations from Structural Identity
• PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks
• Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
• Graph Neural Networks with convolutional ARMA filters
• Learning Structural Node Embeddings Via Diffusion Wavelets
• Scaling Graph Neural Networks with Approximate PageRank
• Autoregressive Moving Average Graph Filtering
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• PairNorm: Tackling Oversmoothing in GNNs
• Adaptive Sampling Towards Fast Graph Representation Learning
• Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
• Geom-GCN: Geometric Graph Convolutional Networks
• Graph Wavelet Neural Network
• Flow Smoothing and Denoising: Graph Signal Processing in the Edge-Space
• Non-Local Graph Neural Networks
• Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs

Cited by in corpus (2)

• How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications
• Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs