Not All Neighbors are Friendly

Maurya, Sunil Kumar; Liu, Xin; Murata, Tsuyoshi

doi:10.1145/3511808.3557543

Cited by 3 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We acknowledge that the final subset calculated by DualNetGO is may not the optimal one due to the sampling nature in stage 1 and 2. As training DualNetGO is a stochastic process, a careful choice of the hyperparameters of the epochs in stages 1 and 2 may be necessary to approach the optimal solution, as suggested by another dual-network model that deals with heterophilic graph data (Maurya et al ., 2022). Fortunately, the search of hyperparameters costs little time, and DualNetGO is still more efficient in determining a suitable combination of features than enumerating all possibilities.…”

Section: Methodsmentioning

confidence: 99%

“…As DualNetGO adopts a heuristic strategy to determine the combination instead of enumerating each possibility, a careful choice of the hyperparameters of the epochs in stages 1 and 2 may be necessary to approach the optimal solution, as suggested by another dual-network model that deals with heterophilic graph data (Maurya et al ., 2022). Fortunately, the performances across hyperparameters show an obvious pattern (Supplementary Section 12), and the search of hyperparameters costs little time.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

DualNetGO: A Dual Network Model for Protein Function Prediction via Effective Feature Selection

Chen,

Luo

2023

Preprint

View full text Add to dashboard Cite

MotivationProtein-protein Interaction (PPI) networks are crucial for automatically annotating protein functions. As there are different types of evidence to define PPI networks, multiple PPI networks exist for the same set of proteins to capture their properties from different aspects, creating challenges in effectively utilizing these heterogeneous graphs for protein function prediction. Recently, several deep learning models have combined PPI networks from all evidence, or concatenated all graph embeddings. However, the lack of a delicate selection procedure prevents the effective harness of information from different PPI networks as they vary in densities, structures and noise levels. Consequently, combining protein features indiscriminately could increase the noise level, leading to decreased model performance.ResultsWe develop DualNetGO, a dual network model comprised of a classifier and a selector, to predict protein functions by effectively selecting features from different sources including graph embeddings of PPI networks, protein domain and subcellular location information. Evaluation of DualNetGO on human and mouse datasets in comparison with other network-based models show at least 4.5%, 6.2% and 14.2% improvement on Fmax in BP, MF and CC Gene Ontology categories respectively for human, and 3.3%, 10.6% and 7.7% improvement on Fmax for mouse. We further show that our model is insensitive to the choice of graph embedding method and is time- and memory-saving. These results demonstrate that combining a subset of features including PPI networks and protein attributes selected by our model is more effective in utilizing PPI network information than only using one kind of or concatenating graph embeddings from all kinds of PPI networks.Availability and implementationThe source code of DualNetGO and some of the experiment data are available at:https://github.com/georgedashen/DualNetGO.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

DualNetGO: A Dual Network Model for Protein Function Prediction via Effective Feature Selection

Chen,

Luo

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…� We propose a novel Dual-net GNN architecture to find the optimal subset of features which leads to the better prediction accuracy of the model. Note This paper is an extension to our previous short paper accepted at CIKM' 2022 [36]. In this paper, we provide more comprehensive details on the model architecture and training methodology (include training algorithm), and extend our result section by including experiments on feature selection methods.…”

Section: Introductionmentioning

confidence: 97%

“…Note This paper is an extension to our previous short paper accepted at CIKM’ 2022 [36] . In this paper, we provide more comprehensive details on the model architecture and training methodology (include training algorithm), and extend our result section by including experiments on feature selection methods.…”

Section: Introductionmentioning

confidence: 99%

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

Maurya

Liu²,

Murata

2023

CAAI Trans on Intel Tech

Self Cite

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

Node Classification in Weighted Complex Networks Using Neighborhood Feature Similarity

Shetty,

Bhattacharjee,

Thanmai

2024

IEEE Trans. Emerg. Top. Comput. Intell.

View full text Add to dashboard Cite

Not All Neighbors are Friendly

Cited by 3 publications

References 6 publications

DualNetGO: A Dual Network Model for Protein Function Prediction via Effective Feature Selection

DualNetGO: A Dual Network Model for Protein Function Prediction via Effective Feature Selection

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

Node Classification in Weighted Complex Networks Using Neighborhood Feature Similarity

Contact Info

Product

Resources

About