Graph neural network: Current state of Art, challenges and applications
Several areas in science and engineering have the relationships between their underlying
data which can be represented as graphs, for example, molecular chemistry, node …
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 …
of a device, user, or data source given their IP-plays an essential role in numerous …
Deep generative model for periodic graphs
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 …
polygon mesh. Their generative modeling has great potential in real-world applications such …
Exploring edge disentanglement for node classification
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 …
relation semantics. For example, connections in a social network could indicate friendship …
Towards reasonable budget allocation in untargeted graph structure attacks via gradient debias
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 …
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.
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 …
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
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 …
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
Graph convolutional neural networks (GCNNs) have been successfully applied to a wide
range of problems, including low-dimensional Euclidean structural domains representing …
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 …
flexible methodology for the geotagging of textual big data. The suggested approach …
Surrogate representation learning with isometric mapping for gray-box graph adversarial attacks
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 …
inconspicuous attacks with limited knowledge of the victim model. The details of the victim …