Feature Selection and Extraction for Graph Neural Networks

Acharya, Deepak Bhaskar; Zhang, Huaming

doi:10.1145/3374135.3385309

Cited by 21 publications

(19 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method proposed in the paper Feature Selection and Extraction for Graph Neural Networks (FSEGNN) [1] helps to select the exact features instead of a linear combination of the contribution of the features. Once the size of the features set is reduced, and the model is trained, it still performs well with the graph node classification problem.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…Deepak and Huaming [1] selected Graph Neural Network(GNN) features in the paper feature selection and extraction for Graph Neural Networks, with the citation network datasets. (1) They apply the feature selection algorithm to GNNs using gumbel softmax and conduct a series of tests using various comparison datasets: Cora, Pubmed, and Citeseer.…”

Section: Gumbel Softmax Approach On Feature Selectionmentioning

confidence: 99%

“…The main objective of graph clustering is to find strongly linked subgraphs in a graph, to synthesize the two closest related ones. (1) Within the same graph, the nodes of a graph will be very cohesive but sparsely connected with other sub-graphs.…”

Section: Introductionmentioning

confidence: 99%

“…In this research, we propose the new method for community detection and clustering by extending the gumbel softmax approach that [1] uses to select and extract the features for the Graph Neural Networks(GNNs) in the graph datasets using deep learning-based approach. GNNs are information-processing models that capture the graph dependence through passing the message between the nodes of the graphs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Community Detection Clustering via Gumbel Softmax

Acharya

Zhang

2020

SN COMPUT. SCI.

Self Cite

View full text Add to dashboard Cite

Recently, in many systems such as speech recognition and visual processing, deep learning has been widely implemented. In this research, we are exploring the possibility of using deep learning in community detection among the graph datasets. Graphs have gained growing traction in different fields, including social networks, information graphs, the recommender system, and also life sciences. In this paper, we propose a method of community detection clustering the nodes of various graph datasets. We cluster different category datasets that belong to affiliation networks, animal networks, human contact networks, human social networks, miscellaneous networks. The deep learning role in modeling the interaction between nodes in a network allows a revolution in the field of science relevant to graph network analysis. In this paper, we extend the gumbel softmax approach to graph network clustering. The experimental findings on specific graph datasets reveal that the new approach outperforms traditional clustering significantly, which strongly shows the efficacy of deep learning in graph community detection clustering. We do a series of experiments on our graph clustering algorithm, using various graph datasets: Zachary's karate club, Highland tribes, Train bombing, American Revolution, Dolphins, Zebra, Windsurfers, Les Misérables, Political books.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Gumbel Softmax Approach On Feature Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Community Detection Clustering via Gumbel Softmax

Acharya

Zhang

2020

SN COMPUT. SCI.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this research, we propose the new method for data points clustering and compare our results with recently proposed Nested mini-batch K-Means [16] and benchmarking clustering algorithms such as K-Means, Affinity propagation, Agglomerative clustering, and Mini-batch and K-Means. In the newly proposed method, (1) we address the problem of determining the optimal number of clusters for the datasets used in our experiments by making the analysis using Gap statistics [23], and then (2) using our method, we extend the gumbel softmax approach that [2] and [1] uses to select and extract the features for the Graph Neural Networks(GNNs) in the graph datasets using a deep learning-based approach and community detection via gumbel softmax, respectively.…”

Section: Introductionmentioning

confidence: 99%

Data Points Clustering via Gumbel Softmax

Acharya

Zhang

2021

SN COMPUT. SCI.

Self Cite

View full text Add to dashboard Cite

Finding useful patterns in the dataset has been a fascinating topic, and one of the most researched problems in this area is identifying the cluster groups within the dataset. This research paper introduces a "new data clustering method" called Data Points Clustering via Gumbel Softmax (DPCGS) and demonstrates that it is suitable for clustering the data points datasets. We evaluate DPCGS efficiency and clustering quality through several experiments. Experiments show that statistically relevant clustering structures can be identified with our method, depending on the dataset. We also present a performance comparison table where we use datasets such as Wine, Wheat seeds, Iris, Wisconsin breast cancer and compare the DPCGS results with different benchmarking and recently proposed clustering algorithms such as Birch, K-Means, Affinity propagation, Agglomerative clustering, and Mini-batch K-Means and Nested mini-batch K-Means. Our method DPCGS performs better than most of the previously and recently proposed clustering algorithms.

show abstract