Graph neural network: Current state of Art, challenges and applications

A Gupta, P Matta, B Pant - Materials Today: Proceedings, 2021 - Elsevier
Several areas in science and engineering have the relationships between their underlying
data which can be represented as graphs, for example, molecular chemistry, node …

A Survey on Geolocation on the Internet

A Zilberman, A Offer, B Pincu… - … Surveys & Tutorials, 2024 - ieeexplore.ieee.org
In the interconnected world of the Internet, IP geolocation-identifying the geographic location
of a device, user, or data source given their IP-plays an essential role in numerous …

Deep generative model for periodic graphs

S Wang, X Guo, L Zhao - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Periodic graphs are graphs consisting of repetitive local structures, such as crystal nets and
polygon mesh. Their generative modeling has great potential in real-world applications such …

Exploring edge disentanglement for node classification

T Zhao, X Zhang, S Wang - Proceedings of the ACM Web Conference …, 2022 - dl.acm.org
Edges in real-world graphs are typically formed by a variety of factors and carry diverse
relation semantics. For example, connections in a social network could indicate friendship …

Towards reasonable budget allocation in untargeted graph structure attacks via gradient debias

Z Liu, Y Luo, L Wu, Z Liu, SZ Li - arXiv preprint arXiv:2304.00010, 2023 - arxiv.org
It has become cognitive inertia to employ cross-entropy loss function in classification related
tasks. In the untargeted attacks on graph structure, the gradients derived from the attack …

[PDF][PDF] KDLGT: A Linear Graph Transformer Framework via Kernel Decomposition Approach.

Y Wu, Y Xu, W Zhu, G Song, Z Lin, L Wang, S Liu - IJCAI, 2023 - ijcai.org
In recent years, graph Transformers (GTs) have been demonstrated as a robust architecture
for a wide range of graph learning tasks. However, the quadratic complexity of GTs limits …

[HTML][HTML] A data-driven clustering approach for assessing spatiotemporal vulnerability to urban emergencies

JCN Bittencourt, DG Costa, P Portugal… - Sustainable Cities and …, 2024 - Elsevier
Urban vulnerability to emergencies has become a relevant issue as cities get bigger and the
negative impacts of climatic changes become more prominent. In recent years, smart city …

Superpixel image classification with graph convolutional neural networks based on learnable positional embedding

JH Bae, GH Yu, JH Lee, DT Vu, LH Anh, HG Kim… - Applied Sciences, 2022 - mdpi.com
Graph convolutional neural networks (GCNNs) have been successfully applied to a wide
range of problems, including low-dimensional Euclidean structural domains representing …

Geolocation predicting of tweets using bert-based models

K Lutsai, CH Lampert - arXiv preprint arXiv:2303.07865, 2023 - arxiv.org
This research is aimed to solve the tweet/user geolocation prediction task and provide a
flexible methodology for the geotagging of textual big data. The suggested approach …

Surrogate representation learning with isometric mapping for gray-box graph adversarial attacks

Z Liu, Y Luo, Z Zang, SZ Li - … Conference on Web Search and Data …, 2022 - dl.acm.org
Gray-box graph attacks aim to disrupt the victim model's performance by using
inconspicuous attacks with limited knowledge of the victim model. The details of the victim …