Graph Highway Networks

• URL: http://arxiv.org/abs/2004.04635v1
• Date: Thu, 9 Apr 2020 16:26:43 GMT
• Title: Graph Highway Networks
• Authors: Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M.Jose
• Abstract summary: Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency. They suffer from the notorious over-smoothing problem, in which the learned representations converge to alike vectors when many layers are stacked. We propose Graph Highway Networks (GHNet) which utilize gating units to balance the trade-off between homogeneity and heterogeneity in the GCN learning process.
• Score: 77.38665506495553
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency. However, they suffer from the notorious over-smoothing problem, in which the learned representations of densely connected nodes converge to alike vectors when many (>3) graph convolutional layers are stacked. In this paper, we argue that there-normalization trick used in GCN leads to overly homogeneous information propagation, which is the source of over-smoothing. To address this problem, we propose Graph Highway Networks(GHNet) which utilize gating units to automatically balance the trade-off between homogeneity and heterogeneity in the GCN learning process. The gating units serve as direct highways to maintain heterogeneous information from the node itself after feature propagation. This design enables GHNet to achieve much larger receptive fields per node without over-smoothing and thus access to more of the graph connectivity information. Experimental results on benchmark datasets demonstrate the superior performance of GHNet over GCN and related models.

Related papers

• Improving Graph Neural Networks by Learning Continuous Edge Directions [0.0]
  Graph Neural Networks (GNNs) traditionally employ a message-passing mechanism that resembles diffusion over undirected graphs. Our key insight is to assign fuzzy edge directions to the edges of a graph so that features can preferentially flow in one direction between nodes. We propose a general framework, called Continuous Edge Direction (CoED) GNN, for learning on graphs with fuzzy edges.
  arXiv  Detail & Related papers  (2024-10-18T01:34:35Z)
• Transfer Entropy in Graph Convolutional Neural Networks [0.0]
  Graph Convolutional Networks (GCN) are Graph Neural Networks where the convolutions are applied over a graph. In this study, we address two important challenges related to GCNs: i. Oversmoothing is the degradation of the discriminative capacity of nodes as a result of repeated aggregations. We propose a new strategy for addressing these challenges in GCNs based on Transfer Entropy (TE), which measures of the amount of directed transfer of information between two time varying nodes.
  arXiv  Detail & Related papers  (2024-06-08T20:09:17Z)
• Self-Attention Empowered Graph Convolutional Network for Structure Learning and Node Embedding [5.164875580197953]
  In representation learning on graph-structured data, many popular graph neural networks (GNNs) fail to capture long-range dependencies. This paper proposes a novel graph learning framework called the graph convolutional network with self-attention (GCN-SA) The proposed scheme exhibits an exceptional generalization capability in node-level representation learning.
  arXiv  Detail & Related papers  (2024-03-06T05:00:31Z)
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph [57.2953563124339]
  We propose a novel heterogeneous graph neural network with sequential node representation, namely Seq-HGNN. We conduct extensive experiments on four widely used datasets from Heterogeneous Graph Benchmark (HGB) and Open Graph Benchmark (OGB)
  arXiv  Detail & Related papers  (2023-05-18T07:27:18Z)
• Graph Neural Networks with Feature and Structure Aware Random Walk [7.143879014059894]
  We show that in typical heterphilous graphs, the edges may be directed, and whether to treat the edges as is or simply make them undirected greatly affects the performance of the GNN models. We develop a model that adaptively learns the directionality of the graph, and exploits the underlying long-distance correlations between nodes.
  arXiv  Detail & Related papers  (2021-11-19T08:54:21Z)
• Is Homophily a Necessity for Graph Neural Networks? [50.959340355849896]
  Graph neural networks (GNNs) have shown great prowess in learning representations suitable for numerous graph-based machine learning tasks. GNNs are widely believed to work well due to the homophily assumption ("like attracts like"), and fail to generalize to heterophilous graphs where dissimilar nodes connect. Recent works design new architectures to overcome such heterophily-related limitations, citing poor baseline performance and new architecture improvements on a few heterophilous graph benchmark datasets as evidence for this notion. In our experiments, we empirically find that standard graph convolutional networks (GCNs) can actually achieve better performance than
  arXiv  Detail & Related papers  (2021-06-11T02:44:00Z)
• Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning [68.97378785686723]
  graph neural networks (GNNs) have greatly advanced the performance of node representation learning on graphs. A majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs. We propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes.
  arXiv  Detail & Related papers  (2021-04-04T23:31:39Z)
• An Uncoupled Training Architecture for Large Graph Learning [20.784230322205232]
  We present Node2Grids, a flexible uncoupled training framework for embedding graph data into grid-like data. By ranking each node's influence through degree, Node2Grids selects the most influential first-order as well as second-order neighbors with central node fusion information. For further improving the efficiency of downstream tasks, a simple CNN-based neural network is employed to capture the significant information from the mapped grid-like data.
  arXiv  Detail & Related papers  (2020-03-21T11:49:16Z)
• Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks [183.97265247061847]
  We leverage graph signal processing to characterize the representation space of graph neural networks (GNNs) We discuss the role of graph convolutional filters in GNNs and show that any architecture built with such filters has the fundamental properties of permutation equivariance and stability to changes in the topology. We also study the use of GNNs in recommender systems and learning decentralized controllers for robot swarms.
  arXiv  Detail & Related papers  (2020-03-08T13:02:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.