Related papers: AeTHERON: Autoregressive Topology-aware Heterogene…

Increased attention has been paid over the last four years to dynamic network embedding. Existing dynamic embedding methods, however, consider the problem as limited to the evolution of a topology over a sequence of global, discrete states.…

We propose a general architecture that combines the coefficient learning scheme with a residual operator layer for learning mappings between continuous functions in the 3D Euclidean space. Our proposed model is guaranteed to achieve…

Urban water-surface robust perception serves as the foundation for intelligent monitoring of aquatic environments and the autonomous navigation and operation of unmanned vessels, especially in the context of waterway safety. It is worth…

We propose a novel neural network architecture, called autoencoder-constrained graph convolutional network, to solve node classification task on graph domains. As suggested by its name, the core of this model is a convolutional network…

An elastic rod is a long and thin body able to sustain large global deformations, even if local strains are small. The Cosserat rod is a non-linear elastic rod with an oriented centreline, which enables modelling of bending, stretching and…

Deep learning models can take weeks to train on a single GPU-equipped machine, necessitating scaling out DL training to a GPU-cluster. However, current distributed DL implementations can scale poorly due to substantial parameter…

Individuals or companies in a large social or financial network often display rather heterogeneous behaviors for various reasons. In this work, we propose a network vector autoregressive model with a latent group structure to model…

Capturing the dynamics of active particles, i.e., small self-propelled agents that both deform and are deformed by a fluid in which they move is a formidable problem as it requires coupling fine scale hydrodynamics with large scale…

To enable heterogeneous computing systems with autonomous programming and optimization capabilities, we propose a unified, end-to-end, programmable graph representation learning (PGL) framework that is capable of mining the complexity of…

Efficient scheduling of directed acyclic graphs (DAGs) in heterogeneous environments is challenging due to resource capacities and dependencies. In practice, the need for adaptability across environments with varying resource pools and task…

Many real-world prediction tasks, particularly those involving entities such as customers or patients, involve both {sequential} and {relational} data. Each entity maintains its own sequence of events while simultaneously engaging in…

Graph Neural Networks (GNNs) face a fundamental adaptability challenge: their fixed message-passing architectures struggle with the immense diversity of real-world graphs, where optimal computational strategies vary by local structure and…

We propose a novel algorithm for sleep dynamics visualization and automatic annotation by applying diffusion geometry based sensor fusion algorithm to fuse spectral information from two electroencephalograms (EEG). The diffusion geometry…

Graph neural networks have been a powerful tool for mesh-based physical simulation. To efficiently model large-scale systems, existing methods mainly employ hierarchical graph structures to capture multi-scale node relations. However, these…

We study generative modeling of graphs with recurring subgraph motifs. We propose Flowette, a continuous flow matching framework that employs a graph neural network-based transformer to learn a velocity field over graph representations with…

This work presents a unified framework for the unsupervised prediction of physically plausible interpolations between two 3D articulated shapes and the automatic estimation of dense correspondence between them. Interpolation is modelled as…

This article presents a graph neural network (GNN) based surrogate modeling approach for fluid-acoustic shape optimization. The GNN model transforms mesh-based simulations into a computational graph, enabling global prediction of pressure…

We present numerical simulations of active fluid droplets immersed in an external fluid in 2-dimensions { using} an Immersed Boundary method to simulate the fluid droplet interface as a Lagrangian mesh. We present results from two example…

Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph. However, on the one hand, most of existing heterogeneous graph…

We propose FlowReg, a deep learning-based framework for unsupervised image registration for neuroimaging applications. The system is composed of two architectures that are trained sequentially: FlowReg-A which affinely corrects for gross…