TopoBenchmarkX: A Framework for Benchmarking Topological Deep Learning
L Telyatnikov, G Bernardez, M Montagna… - arXiv preprint arXiv …, 2024 - arxiv.org
This work introduces TopoBenchmarkX, a modular open-source library designed to
standardize benchmarking and accelerate research in Topological Deep Learning (TDL) …
standardize benchmarking and accelerate research in Topological Deep Learning (TDL) …
Generalizing Topological Graph Neural Networks with Paths
While Graph Neural Networks (GNNs) have made significant strides in diverse areas, they
are hindered by a theoretical constraint known as the 1-Weisfeiler-Lehmann test. Even …
are hindered by a theoretical constraint known as the 1-Weisfeiler-Lehmann test. Even …
Nonlinear Sheaf Diffusion in Graph Neural Networks
O Zaghen - arXiv preprint arXiv:2403.00337, 2024 - arxiv.org
This work focuses on exploring the potential benefits of introducing a nonlinear Laplacian in
Sheaf Neural Networks for graph-related tasks. The primary aim is to understand the impact …
Sheaf Neural Networks for graph-related tasks. The primary aim is to understand the impact …
Random Abstract Cell Complexes
We define a model for random (abstract) cell complexes (CCs), similiar to the well-known
Erd\H {o} sR\'enyi model for graphs and its extensions for simplicial complexes. To build a …
Erd\H {o} sR\'enyi model for graphs and its extensions for simplicial complexes. To build a …
Topological Graph Signal Compression
Recently emerged Topological Deep Learning (TDL) methods aim to extend current Graph
Neural Networks (GNN) by naturally processing higher-order interactions, going beyond the …
Neural Networks (GNN) by naturally processing higher-order interactions, going beyond the …
Combinatorial Complex Score-based Diffusion Modelling through Stochastic Differential Equations
A Carrel - arXiv preprint arXiv:2406.04916, 2024 - arxiv.org
Graph structures offer a versatile framework for representing diverse patterns in nature and
complex systems, applicable across domains like molecular chemistry, social networks, and …
complex systems, applicable across domains like molecular chemistry, social networks, and …
Interaction Event Forecasting in Multi-Relational Recursive HyperGraphs: A Temporal Point Process Approach
T Gracious, A Dukkipati - arXiv preprint arXiv:2404.17943, 2024 - arxiv.org
Modeling the dynamics of interacting entities using an evolving graph is an essential
problem in fields such as financial networks and e-commerce. Traditional approaches focus …
problem in fields such as financial networks and e-commerce. Traditional approaches focus …
SIMAP: A simplicial-map layer for neural networks
R Gonzalez-Diaz, MA Gutiérrez-Naranjo… - arXiv preprint arXiv …, 2024 - arxiv.org
In this paper, we present SIMAP, a novel layer integrated into deep learning models, aimed
at enhancing the interpretability of the output. The SIMAP layer is an enhanced version of …
at enhancing the interpretability of the output. The SIMAP layer is an enhanced version of …
[HTML][HTML] 基于多粒度的图对比学习推荐算法
吴鹏飞， 苏凡军 - Modeling and Simulation, 2024 - hanspub.org
现有的图对比学习推荐算法, 多局限于节点级或图级的对比学习, 未能综合利用图的信息.
针对这个问题, 提出了一种基于多粒度的图对比学习推荐算法(Multi-Granularity Graph …
针对这个问题, 提出了一种基于多粒度的图对比学习推荐算法(Multi-Granularity Graph …
Securing P2P resource sharing via blockchain and GNN-based trust
B Badr - 2024 - theses.hal.science
The emergence of blockchain technology and cryptocurrencies has enabled the
development of innovative peer-to-peer (P2P) models for resource allocation, sharing, and …
development of innovative peer-to-peer (P2P) models for resource allocation, sharing, and …