Tracing the Propagation Path: A Flow Perspective of Representation Learning on Graphs
This addresses scalability and depth limitations in graph representation learning for researchers and practitioners, though it appears incremental as it builds on existing GCN paradigms.
The paper tackles the challenges of shallow structures and poor scalability in Graph Convolutional Networks (GCNs) by proposing a new framework called Flow Graph Network (FlowGN), which uses a 'Source→Sink' information propagation mode and decouples layers from propagation, leading to improved performance on public datasets.
Graph Convolutional Networks (GCNs) have gained significant developments in representation learning on graphs. However, current GCNs suffer from two common challenges: 1) GCNs are only effective with shallow structures; stacking multiple GCN layers will lead to over-smoothing. 2) GCNs do not scale well with large, dense graphs due to the recursive neighborhood expansion. We generalize the propagation strategies of current GCNs as a \emph{"Sink$\to$Source"} mode, which seems to be an underlying cause of the two challenges. To address these issues intrinsically, in this paper, we study the information propagation mechanism in a \emph{"Source$\to$Sink"} mode. We introduce a new concept "information flow path" that explicitly defines where information originates and how it diffuses. Then a novel framework, namely Flow Graph Network (FlowGN), is proposed to learn node representations. FlowGN is computationally efficient and flexible in propagation strategies. Moreover, FlowGN decouples the layer structure from the information propagation process, removing the interior constraint of applying deep structures in traditional GCNs. Further experiments on public datasets demonstrate the superiority of FlowGN against state-of-the-art GCNs.