Graph Pointer Neural Networks

by   Tianmeng Yang, et al.
Peking University

Graph Neural Networks (GNNs) have shown advantages in various graph-based applications. Most existing GNNs assume strong homophily of graph structure and apply permutation-invariant local aggregation of neighbors to learn a representation for each node. However, they fail to generalize to heterophilic graphs, where most neighboring nodes have different labels or features, and the relevant nodes are distant. Few recent studies attempt to address this problem by combining multiple hops of hidden representations of central nodes (i.e., multi-hop-based approaches) or sorting the neighboring nodes based on attention scores (i.e., ranking-based approaches). As a result, these approaches have some apparent limitations. On the one hand, multi-hop-based approaches do not explicitly distinguish relevant nodes from a large number of multi-hop neighborhoods, leading to a severe over-smoothing problem. On the other hand, ranking-based models do not joint-optimize node ranking with end tasks and result in sub-optimal solutions. In this work, we present Graph Pointer Neural Networks (GPNN) to tackle the challenges mentioned above. We leverage a pointer network to select the most relevant nodes from a large amount of multi-hop neighborhoods, which constructs an ordered sequence according to the relationship with the central node. 1D convolution is then applied to extract high-level features from the node sequence. The pointer-network-based ranker in GPNN is joint-optimized with other parts in an end-to-end manner. Extensive experiments are conducted on six public node classification datasets with heterophilic graphs. The results show that GPNN significantly improves the classification performance of state-of-the-art methods. In addition, analyses also reveal the privilege of the proposed GPNN in filtering out irrelevant neighbors and reducing over-smoothing.


page 1

page 2

page 3

page 4


MHNF: Multi-hop Heterogeneous Neighborhood information Fusion graph representation learning

Attention mechanism enables the Graph Neural Networks(GNNs) to learn the...

LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity

Heterophily has been considered as an issue that hurts the performance o...

NAGphormer: Neighborhood Aggregation Graph Transformer for Node Classification in Large Graphs

Graph Transformers have demonstrated superiority on various graph learni...

Multi-hop assortativities for networks classification

Several social, medical, engineering and biological challenges rely on d...

Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs

Graph Neural Networks (GNNs) have shown excellent performance on graphs ...

TPGNN: Learning High-order Information in Dynamic Graphs via Temporal Propagation

Temporal graph is an abstraction for modeling dynamic systems that consi...

Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation

Graph neural networks (GNNs) have emerged as a powerful paradigm for emb...

Please sign up or login with your details

Forgot password? Click here to reset