Results 231 to 240 of about 1,143,028 (268)

Adversarially Trained Persistent Homology Based Graph Convolutional Network for Disease Identification Using Brain Connectivity

IEEE Transactions on Medical Imaging, 2023
Brain disease propagation is associated with characteristic alterations in the structural and functional connectivity networks of the brain. To identify disease-specific network representations, graph convolutional networks (GCNs) have been used because ...
C. Bian, N. Xia, A. Xie, S. Cong, Q. Dong   +4 more
semanticscholar   +1 more source

Topological data analysis and topological deep learning beyond persistent homology: a review

Artificial Intelligence Review
Topological data analysis (TDA) is a rapidly evolving field in applied mathematics and data science that leverages tools from topology to uncover robust, shape-driven, and explainable insights in complex datasets.
Zhe Su, Xiang Liu, Layal Bou Hamdan, Vasileios Maroulas, Jie Wu, Gunnar E. Carlsson, Guo-Wei Wei   +6 more
semanticscholar   +1 more source

Boosting Graph Pooling with Persistent Homology

Neural Information Processing Systems
Recently, there has been an emerging trend to integrate persistent homology (PH) into graph neural networks (GNNs) to enrich expressive power. However, naively plugging PH features into GNN layers always results in marginal improvement with low ...
Chaolong Ying, Xinjian Zhao, Tianshu Yu
semanticscholar   +1 more source

Differentiability and Optimization of Multiparameter Persistent Homology

International Conference on Machine Learning
Real-valued functions on geometric data -- such as node attributes on a graph -- can be optimized using descriptors from persistent homology, allowing the user to incorporate topological terms in the loss function.
Luis Scoccola, S. Setlur, David Loiseaux, Mathieu Carrière, Steve Oudot   +4 more
semanticscholar   +1 more source

Improving Self-supervised Molecular Representation Learning using Persistent Homology

Neural Information Processing Systems, 2023
Self-supervised learning (SSL) has great potential for molecular representation learning given the complexity of molecular graphs, the large amounts of unlabelled data available, the considerable cost of obtaining labels experimentally, and the hence ...
Yuankai Luo, Lei Shi, Veronika Thost
semanticscholar   +1 more source

Graphcode: Learning from multiparameter persistent homology using graph neural networks

Neural Information Processing Systems
We introduce graphcodes, a novel multi-scale summary of the topological properties of a dataset that is based on the well-established theory of persistent homology. Graphcodes handle datasets that are filtered along two real-valued scale parameters. Such
Michael Kerber, Florian Russold
semanticscholar   +1 more source

Persistent homology for high-dimensional data based on spectral methods

Neural Information Processing Systems, 2023
Persistent homology is a popular computational tool for analyzing the topology of point clouds, such as the presence of loops or voids. However, many real-world datasets with low intrinsic dimensionality reside in an ambient space of much higher ...
Sebastian Damrich, Philipp Berens, D. Kobak   +2 more
semanticscholar   +1 more source

Descriptor generation from Morgan fingerprint using persistent homology

SAR and QSAR in environmental research (Print)
In cheminformatics, molecular fingerprints (FPs) are used in various tasks such as regression and classification. However, predictive models often underutilize Morgan FP for regression and related tasks in machine learning.
T. Ehiro
semanticscholar   +1 more source

Persistent homology and topological statistics of hyperuniform point clouds

Physical Review Research
Hyperuniformity, the suppression of density fluctuations at large length scales, is observed across a wide variety of domains, from cosmology to condensed matter and biological systems.
M. Salvalaglio, Dominic J. Skinner, Jörn Dunkel, Axel Voigt   +3 more
semanticscholar   +1 more source

Adsorbate Organization Characterized by Sublevelset Persistent Homology.

Journal of Chemical Theory and Computation, 2023
Interfacial adsorbate organization influences a variety physicochemical properties and reactivity. Surfaces that are rough, defect laden, or have large fluctuations (as in soft matter interfaces) can lead to complex adsorbate structures.
Nitesh Kumar, A. Clark
semanticscholar   +1 more source