Graph Neural Networks in Urban Intelligence

Li, Yanhua; Zhou, Xun; Pan, Menghai

doi:10.1007/978-981-16-6054-2_27

Cited by 8 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural network explainers are a crucial category of research tools designed to elucidate and explain the predictions generated by neural network models. The goal of these explainers is to generate explanatory results to help explain the model’s predictions [ 56 , 57 ]. For example, GNNexplainer [ 45 ] identifies the most influential nodes and edges in the subgraph by extracting local subgraphs around the target nodes and training additional explanatory modules.…”

Section: Related Workmentioning

confidence: 99%

BPP: a platform for automatic biochemical pathway prediction

Yi,

Liu,

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

A biochemical pathway consists of a series of interconnected biochemical reactions to accomplish specific life activities. The participating reactants and resultant products of a pathway, including gene fragments, proteins, and small molecules, coalesce to form a complex reaction network. Biochemical pathways play a critical role in the biochemical domain as they can reveal the flow of biochemical reactions in living organisms, making them essential for understanding life processes. Existing studies of biochemical pathway networks are mainly based on experimentation and pathway database analysis methods, which are plagued by substantial cost constraints. Inspired by the success of representation learning approaches in biomedicine, we develop the biochemical pathway prediction (BPP) platform, which is an automatic BPP platform to identify potential links or attributes within biochemical pathway networks. Our BPP platform incorporates a variety of representation learning models, including the latest hypergraph neural networks technology to model biochemical reactions in pathways. In particular, BPP contains the latest biochemical pathway-based datasets and enables the prediction of potential participants or products of biochemical reactions in biochemical pathways. Additionally, BPP is equipped with an SHAP explainer to explain the predicted results and to calculate the contributions of each participating element. We conduct extensive experiments on our collected biochemical pathway dataset to benchmark the effectiveness of all models available on BPP. Furthermore, our detailed case studies based on the chronological pattern of our dataset demonstrate the effectiveness of our platform. Our BPP web portal, source code and datasets are freely accessible at https://github.com/Glasgow-AI4BioMed/BPP.

show abstract

Section: Related Workmentioning

confidence: 99%

BPP: a platform for automatic biochemical pathway prediction

Yi,

Liu,

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…APPNP [31], JK [32], Geom‐GCN [16], SimP‐GCN [45], and CPGNN [18] aim to improve the feature propagation scheme within layers of the model. More recently, researchers are proposing to make GNN models deeper [27, 29, 30]. However, deeper models suffer from over‐smoothing, where after stacking many GNN layers, features of the node become indistinguishable from each other, and there is a drop in the performance of the model.…”

Section: Related Workmentioning

confidence: 99%

“…GCNII [27] use residual connections and identity mapping in GNN layers to enable deeper networks. RevGNN [29] uses deep reversible architectures and [30] uses noise regularisation to train deep GNN models. Recently researchers have proposed new datasets that do not follow homophily assumption in traditional GNN models.…”

Section: Related Workmentioning

confidence: 99%

“…Thus, any feature aggregation by GNN with strict homophily assumption may often cause the addition of noisy features and may reduce the signal present in node features to learn effectively. Researchers have explored many ways to tackle this challenge by proposing many improvements in model design, for example, making models deeper [27, 29, 30], using attention layers [24], residual layers [27, 31, 32], etc. However, most of these solutions attempt to fit the model to the noisy data in an effective way [33, 34].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feature selection: Key to enhance node classification with graph neural networks

Maurya

Liu²,

Murata

2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Graphs help to define the relationships between entities in the data. These relationships, represented by edges, often provide additional context information which can be utilised to discover patterns in the data. Graph Neural Networks (GNNs) employ the inductive bias of the graph structure to learn and predict on various tasks. The primary operation of graph neural networks is the feature aggregation step performed over neighbours of the node based on the structure of the graph. In addition to its own features, for each hop, the node gets additional combined features from its neighbours. These aggregated features help define the similarity or dissimilarity of the nodes with respect to the labels and are useful for tasks like node classification. However, in real-world data, features of neighbours at different hops may not correlate with the node's features. Thus, any indiscriminate feature aggregation by GNN might cause the addition of noisy features leading to degradation in model's performance. In this work, we show that selective aggregation of node features from various hops leads to better performance than default aggregation on the node classification task. Furthermore, we propose a Dual-Net GNN architecture with a classifier model and a selector model. The classifier model trains over a subset of input node features to predict node labels while the selector model learns to provide optimal input subset to the classifier for the best performance. These two models are trained jointly to learn the best subset of features that give higher accuracy in node label predictions. With extensive experiments, we show that our proposed model outperforms both feature selection methods and state-of-the-art GNN models with remarkable improvements up to 27.8%.

show abstract

“…While oversmoothing deteriorates the performance in GNNs, efforts have been made to preserve the identity of individual messages by modifying the message passing scheme, such as introducing jump connections (Xu et al, 2018;Chen et al, 2020b), sampling neighboring nodes and edges (Rong et al, 2019;Feng et al, 2020), adding regularizations (Chen et al, 2020a;Zhou et al, 2020;Yang et al, 2021), and increasing the complexity of convolutional layers (Balcilar et al, 2021;Geerts et al, 2021;Bodnar et al, 2021;. Other methods try to trade-off graph smoothness with the fitness of the encoded features (Zhu et al, 2021; or postpone the occurrence of oversmoothing by mechanisms, such as residual networks (Li et al, 2021a; and the diffusion scheme (Chamberlain et al, 2021;Zhao et al, 2021).…”

Section: Oversmoothness In Graph Representationmentioning

confidence: 99%

Framelet Message Passing

Liu¹,

Zhou²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Graph neural networks (GNNs) have achieved champion in wide applications. Neural message passing is a typical key module for feature propagation by aggregating neighboring features. In this work, we propose a new message passing based on multiscale framelet transforms, called Framelet Message Passing. Different from traditional spatial methods, it integrates framelet representation of neighbor nodes from multiple hops away in node message update. We also propose a continuous message passing using neural ODE solvers. It turns both discrete and continuous cases can provably achieve network stability and limit oversmoothing due to the multiscale property of framelets. Numerical experiments on real graph datasets show that the continuous version of the framelet message passing significantly outperforms existing methods when learning heterogeneous graphs and achieves state-of-the-art performance on classic node classification tasks with low computational costs.

show abstract

Graph Neural Networks in Urban Intelligence

Cited by 8 publications

References 0 publications

BPP: a platform for automatic biochemical pathway prediction

BPP: a platform for automatic biochemical pathway prediction

Feature selection: Key to enhance node classification with graph neural networks

Framelet Message Passing

Contact Info

Product

Resources

About