PushNet: Efficient and Adaptive Neural Message Passing

by   Julian Busch, et al.
Universität München

Message passing neural networks have recently evolved into a state-of-the-art approach to representation learning on graphs. Existing methods perform synchronous message passing along all edges in multiple subsequent rounds and consequently suffer from various shortcomings: Propagation schemes are inflexible since they are restricted to k-hop neighborhoods and insensitive to actual demands of information propagation. Further, long-range dependencies cannot be modeled adequately and learned representations are based on correlations of fixed locality. These issues prevent existing methods from reaching their full potential in terms of prediction performance. Instead, we consider a novel asynchronous message passing approach where information is pushed only along the most relevant edges until convergence. Our proposed algorithm can equivalently be formulated as a single synchronous message passing iteration using a suitable neighborhood function, thus sharing the advantages of existing methods while addressing their central issues. The resulting neural network utilizes a node-adaptive receptive field derived from meaningful sparse node neighborhoods. In addition, by learning and combining node representations over differently sized neighborhoods, our model is able to capture correlations on multiple scales. We further propose variants of our base model with different inductive bias. Empirical results are provided for semi-supervised node classification on five real-world datasets following a rigorous evaluation protocol. We find that our models outperform competitors on all datasets in terms of accuracy with statistical significance. In some cases, our models additionally provide faster runtime.


page 1

page 2

page 3

page 4


Framelet Message Passing

Graph neural networks (GNNs) have achieved champion in wide applications...

Leave Graphs Alone: Addressing Over-Squashing without Rewiring

Recent works have investigated the role of graph bottlenecks in preventi...

ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs

Many real-world data can be modeled as 3D graphs, but learning represent...

DRew: Dynamically Rewired Message Passing with Delay

Message passing neural networks (MPNNs) have been shown to suffer from t...

Addressing Heterophily in Node Classification with Graph Echo State Networks

Node classification tasks on graphs are addressed via fully-trained deep...

Ewald-based Long-Range Message Passing for Molecular Graphs

Neural architectures that learn potential energy surfaces from molecular...

A Message Passing Algorithm for the Problem of Path Packing in Graphs

We consider the problem of packing node-disjoint directed paths in a dir...

Please sign up or login with your details

Forgot password? Click here to reset