Graph Highway Networks

2020-04-09 · Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M. Jose

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.

📄 PDF Abstract BibTeX arXiv:2004.04635

Code (1)

gcucurull/jax-ghnet jax

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Highway Graph to Accelerate Reinforcement Learning

2024-05-20 · Zidu Yin, Zhen Zhang, Dong Gong, Stefano V. Albrecht 외

Reinforcement Learning (RL) algorithms often struggle with low training efficiency. A common approach to address this challenge is integrating model-based planning algorithms, such as Monte Carlo Tree Search (MCTS) or Va…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Transfer Learning with Graph Neural Networks for Short-Term Highway Traffic Forecasting

2020-04-17 · Tanwi Mallick, Prasanna Balaprakash, Eric Rask, Jane Macfarlane

Highway traffic modeling and forecasting approaches are critical for intelligent transportation systems. Recently, deep-learning-based traffic forecasting methods have emerged as state of the art for a wide range of traf…

Graph Neural Network Time Series Analysis Transfer Learning

Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting

2019-09-24 · Tanwi Mallick, Prasanna Balaprakash, Eric Rask, Jane Macfarlane

Traffic forecasting approaches are critical to developing adaptive strategies for mobility. Traffic patterns have complex spatial and temporal dependencies that make accurate forecasting on large highway networks a chall…

graph partitioning Management

Attention-based Dynamic Graph Convolutional Recurrent Neural Network for Traffic Flow Prediction in Highway Transportation

2023-09-13 · Tianpu Zhang, Weilong Ding, Mengda Xing

As one of the important tools for spatial feature extraction, graph convolution has been applied in a wide range of fields such as traffic flow prediction. However, current popular works of graph convolution cannot guara…

HighwayGraph: Modelling Long-distance Node Relations for Improving General Graph Neural Network

2019-11-10 · Deli Chen, Xiaoqian Liu, Yankai Lin, Peng Li 외

Graph Neural Networks (GNNs) are efficient approaches to process graph-structured data. Modelling long-distance node relations is essential for GNN training and applications. However, conventional GNNs suffer from bad pe…

General Classification Graph Neural Network Node Classification