Sign Up Sign In

Summary

Top 9 papers analyzed

Here is a answer [Kipf et.al.] Kipf, T.N. and Welling, M., 2016, February. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations (ICLR) (Vol. 35) [Hamilton et.al.] Hamilton, W., Ying, Z., and Leskovec, J., 2017. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems (pp. 1024-1034). [Zhou, et.al.] Zhou, L., Qu, M., Tomotani, D., Yu, D., Zitnik, M., Pillai, D. and Zhou, J., 2019, April. Graph convolutional networks meet markov random fields: Semi-supervised community detection in attributed networks. In The World Wide Web Conference (pp. 1349-1359). [Baldoni,et.al.] Baldoni, R., Cervini, L., and Sohrabpour, S., 2020. Deep graphencode: Learning graph representations for node classification. arXiv preprint arXiv:2008.10719. [Veličković,et.al.] Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., and Bengio, Y., 2017. Graph attention networks. arXiv preprint arXiv:1710.10903. [Gao,et.al.] Gao, H., Wang, Z., and Ji, S., 2018. Large-scale learnable graph convolutional networks. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 1416-1424). [Grover, et.al.] Grover, A. and Leskovec, J., 2016. Node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 855-864). [Hamilton et.al.] Hamilton, W.L., Ying, R. and Leskovec, J., 2017. Inductive representation learning on large graphs. In Advances in neural information processing systems (pp. 1025-1035).

A unified framework on node classification using graph convolutional networks

There was a 508 error with the request, suggesting possible solutions and no charge for assistance.

Published By:

S Mithe, K Potika - 2020 Second International Conference on …, 2020 - ieeexplore.ieee.org

Cited By:

0

GatedGCN with GraphSage to Solve Traveling Salesman Problem

An extension of the Lin-Kernighan-Helsgaun TSP solver for constrained traveling salesman and vehicle routing problems, and approximation algorithms for NP-hard problems. Solve traveling salesman problem by Monte Carlo tree search and deep neural network.

Published By:

H Yang - International Conference on Artificial Neural Networks, 2023 - Springer

Cited By:

0

Graph adversarial attacks and defense: An empirical study on citation graph

Graph representations are commonly used for analyzing relationships and comparing larger graphs. They can be applied to various domains such as white-collar crime, drug repurposing, and financial forecasting.

Published By:

C Pham, V Pham, T Dang - … Conference on Big Data (Big Data), 2020 - ieeexplore.ieee.org

Cited By:

0

Exploring graph neural networks for semantic enrichment: Room type classification

An improved GNN algorithm, SAGE-E, achieved 79% accuracy in semantic enrichment of BIM models. SAGE-E showed potential for processing BIM models represented as graphs.

Published By:

Z Wang, R Sacks, T Yeung - Automation in Construction, 2022 - Elsevier

Cited By:

0

A feature-importance-aware and robust aggregator for GCN

LA-GCNMask uses masks to aggregate neighbors; it allows end-to-end training and attention for graph data.

Published By:

L Zhang, H Lu - Proceedings of the 29th ACM International Conference …, 2020 - dl.acm.org

Cited By:

0

A Recommender for Research Collaborators Using Graph Neural Networks

The text discusses how link predictions work by predicting future associations between nodes in a network based on current states. Memory modules store past interactions of nodes up to a certain time, serving as compressed representations.

Published By:

J Zhu, A Yaseen - Frontiers in Artificial Intelligence, 2022 - frontiersin.org

Cited By:

0

DigGCN: Learning compact graph convolutional networks via diffusion aggregation

The article introduces a compact graph convolutional network framework that addresses aggregation issues in GNNs by leveraging diffusion paths and sparsity regularization. The proposed model demonstrates effectiveness for unsupervised feature learning and supervised classification in network embedding tasks.

Published By:

M Lei, P Quan, R Ma, Y Shi, L Niu - IEEE Transactions on …, 2020 - ieeexplore.ieee.org

Cited By:

0

Inductive representation learning on large graphs

This works presents GraphSAGE, which creates node embeddings from a node's local neighborhood.It outperforms baselines on classification tasks across datasets and scales to large graphs.

Published By:

W Hamilton, Z Ying, J Leskovec - Advances in neural …, 2017 - proceedings.neurips.cc

Cited By:

0

Sampling methods for efficient training of graph convolutional networks: A survey

Variance reduction and elimination techniques.

Published By:

X Liu, M Yan, L Deng, G Li, X Ye… - IEEE/CAA Journal of …, 2021 - ieeexplore.ieee.org

Cited By:

0