Edge Attention-based Multi-Relational Graph Convolutional Networks

Chen, Shang; Liu, Qinqing; Chen, Ko-Shin; Sun, Jun; Lü, Jin; Yi, Jinfeng; Bi, Jinbo

doi:10.48550/arxiv.1802.04944

Cited by 26 publications

(29 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some existing models consider edge attributes [16,20,23,30,32,35], but none of these models is directly applicable to our setting since they either consider multi-relational graphs or additionally focus on node attributes. Other existing models [26,31,37] focus on more specific tasks which differ from our setting.…”

Section: Related Workmentioning

confidence: 99%

NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification

Busch,

Kocheturov,

Tresp

et al. 2021

Preprint

View full text Add to dashboard Cite

Malicious software (malware) poses an increasing threat to the security of communication systems as the number of interconnected mobile devices increases exponentially. While some existing malware detection and classification approaches successfully leverage network traffic data, they treat network flows between pairs of endpoints independently and thus fail to leverage rich communication patterns present in the complete network. Our approach first extracts flow graphs and subsequently classifies them using a novel graph neural network model. We present three variants of our base model, which support malware detection and classification in supervised and unsupervised settings. We evaluate our approach on flow graphs that we extract from a recently published dataset for mobile malware detection that addresses several issues with previously available datasets. Experiments on four different prediction tasks consistently demonstrate the advantages of our approach and show that our graph neural network model can boost detection performance by a significant margin. CCS CONCEPTS• Security and privacy → Intrusion/anomaly detection and malware mitigation; • Computing methodologies → Supervised learning by classification; Neural networks; Anomaly detection.

show abstract

Section: Related Workmentioning

confidence: 99%

NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification

Busch,

Kocheturov,

Tresp

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A molecule could be represented as a graph based on its chemical structure, e.g., consider the atoms as the nodes, and the chemical bonds between the atoms as the edges. Thus, many graph theoretic algorithms could be applied to represent a molecule by embedding the graph features into a continuous vector [58,28,49]. A noted study proposed the idea of neural fingerprints, which applies convolutional neural networks on graphs directly [9].…”

Section: A Related Work In Detailsmentioning

confidence: 99%

Multi-View Graph Neural Networks for Molecular Property Prediction

Ma,

Bian,

Rong

et al. 2020

Preprint

View full text Add to dashboard Cite

The crux of molecular property prediction is to generate meaningful representations of the molecules. One promising route is to exploit the molecular graph structure through Graph Neural Networks (GNNs). It is well known that both atoms and bonds significantly affect the chemical properties of a molecule, so an expressive model shall be able to exploit both node (atom) and edge (bond) information simultaneously. Guided by this observation, we present Multi-View Graph Neural Network (MV-GNN), a multi-view message passing architecture to enable more accurate predictions of molecular properties. In MV-GNN, we introduce a shared self-attentive readout component and disagreement loss to stabilize the training process. This readout component also renders the whole architecture interpretable. We further boost the expressive power of MV-GNN by proposing a cross-dependent message passing scheme that enhances information communication of the two views, which results in the MV-GNN cross variant. Lastly, we theoretically justify the expressiveness of the two proposed models in terms of distinguishing nonisomorphism graphs. Extensive experiments demonstrate that MV-GNN models achieve remarkably superior performance over the state-of-the-art models on a variety of challenging benchmarks. Meanwhile, visualization results of the node importance are consistent with prior knowledge, which confirms the interpretability power of MV-GNN models.

show abstract

“…Different from the state of art GNN architecture, i.e. graph convolution networks (GCN) [8] and graph attention networks (GAT) [15], some GNNs can exploit the edge information on graph [6,13,16]. Here, we consider weighted and directed graphs, and develop the graph neural network that uses both nodes and edges weights, where edge weights affect message aggregation.…”

Section: Gnn Utilizing Edge Weightmentioning

confidence: 99%

Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification

Saúde

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Real data collected from different applications that have additional topological structures and connection information are amenable to be represented as a weighted graph. Considering the node labeling problem, Graph Neural Networks (GNNs) is a powerful tool, which can mimic experts' decision on node labeling. GNNs combine node features, connection patterns, and graph structure by using a neural network to embed node information and pass it through edges in the graph. We want to identify the patterns in the input data used by the GNN model to make a decision and examine if the model works as we desire. However, due to the complex data representation and non-linear transformations, explaining decisions made by GNNs is challenging. In this work, we propose new graph features' explanation methods to identify the informative components and important node features. Besides, we propose a pipeline to identify the key factors used for node classification. We use four datasets (two synthetic and two real) to validate our methods. Our results demonstrate that our explanation approach can mimic data patterns used for node classification by human interpretation and disentangle different features in the graphs. Furthermore, our explanation methods can be used for understanding data, debugging GNN models, and examine model decisions.

show abstract

Edge Attention-based Multi-Relational Graph Convolutional Networks

Cited by 26 publications

References 19 publications

NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification

NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification

Multi-View Graph Neural Networks for Molecular Property Prediction

Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification

Contact Info

Product

Resources

About