Exploiting Edge Features in Graph Neural Networks.

By Liyu Gong, Qiang Cheng. 2018

329 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/6b252cf10b7d273d65f36fe80a73f0a12f6dbccb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Permutation Invariant Graph Generation via Score-Based Generative Modeling (2020, methodology): “However, the model in Gong and Cheng (2019) is not designed for predicting edge features, and the capability to make edgewise prediction is limited by the normalizing operation and the restrictive form of attentions.”
BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis (2020, background): “127 As the graph convolution operations in [17], the node features will be multi128 plied by the edge weights, so that neighbors connected with stronger edges have 129 a larger influence.”
Do Transformers Really Perform Badly for Graph Representation? (2021, methodology): “Except the conventionally used methods to encode edge feature, which are described in previous section, there are several attempts that exploit how to better encode edge features: an attention-based GNN layer is developed in [16] to encode edge features, where the edge feature is weighted by the sim”
Graph Neural Networks for Intelligent Transportation Systems: A Survey (2023, methodology): “To this end, they proposed SCALE-Net based on edge-enhanced graph neural network (EGNN) [123].”
Do Transformers Really Perform Bad for Graph Representation? (2021, methodology): “Except the conventionally used methods to encode edge feature, which are described in previous section, there are several attempts that exploit how to better encode edge features: an attention-based GNN layer is developed in [16] to encode edge features, where the edge feature is weighted by the sim”
A Survey on Trajectory-Prediction Methods for Autonomous Driving (2022, methodology): “SCALE-Net uses a edge-enhance graph convolutional network (EGCN) [131] to learn edge features in the trafﬁc ﬂow.”
GPS-Net: Graph Property Sensing Network for Scene Graph Generation (2020, background): “Besides, it influences the context information for the corresponding node, as shown in recent works [8, 9].”
E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT (2021, background): “Methods such as [15] [16] consider edge features, but only for the purpose of improving node representation for better performance, and not edge classification, which is the aim in NIDSs.”