Dropmessage: Unifying random dropping for graph neural networks

T Fang, Z Xiao, C Wang, J Xu, X Yang… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Abstract Graph Neural Networks (GNNs) are powerful tools for graph representation
learning. Despite their rapid development, GNNs also face some challenges, such as over …

Graph embedding and geometric deep learning relevance to network biology and structural chemistry

P Lecca, M Lecca - Frontiers in Artificial Intelligence, 2023 - frontiersin.org
Graphs are used as a model of complex relationships among data in biological science
since the advent of systems biology in the early 2000. In particular, graph data analysis and …

Robust network enhancement from flawed networks

J Xu, Y Yang, C Wang, Z Liu, J Zhang… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Network data in real-world tends to be error-prone due to incomplete sampling, imperfect
measurements, etc.; this in turn results in inaccurate results when performing network …

Minimizing robust density power-based divergences for general parametric density models

A Okuno - Annals of the Institute of Statistical Mathematics, 2024 - Springer
Density power divergence (DPD) is designed to robustly estimate the underlying distribution
of observations, in the presence of outliers. However, DPD involves an integral of the power …

A stochastic optimization approach to minimize robust density power-based divergences for general parametric density models

A Okuno - arXiv preprint arXiv:2307.05251, 2023 - arxiv.org
Density power divergence (DPD)[Basu et al.(1998), Biometrika], designed to estimate the
underlying distribution of the observations robustly, comprises an integral term of the power …

How the latent geometry of a biological network provides information on its dynamics: the case of the gene network of chronic myeloid leukaemia

P Lecca, G Lombardi, RV Latorre… - Frontiers in cell and …, 2023 - frontiersin.org
Background: The concept of the latent geometry of a network that can be represented as a
graph has emerged from the classrooms of mathematicians and theoretical physicists to …

Hyperlink regression via Bregman divergence

A Okuno, H Shimodaira - Neural Networks, 2020 - Elsevier
A collection of U (∈ N) data vectors is called a U-tuple, and the association strength among
the vectors of a tuple is termed as the hyperlink weight, that is assumed to be symmetric with …

Graph Embedding with Outlier-Robust Ratio Estimation

K Satta, H Sasaki - IEICE TRANSACTIONS on Information and …, 2022 - search.ieice.org
The purpose of graph embedding is to learn a lower-dimensional embedding function for
graph data. Existing methods usually rely on maximum likelihood estimation (MLE), and …

Effective representation learning for graph-structured data with adversarial learning

Q Dai - 2020 - theses.lib.polyu.edu.hk
Graph-structured data is widely existed in real-world applications such as social networks,
paper citation networks and protein-protein interaction networks. It encodes very rich …