Related papers: $\alpha$-SGHN: A Robust Model for Learning Particl…

Graph convolutional neural networks (GCNNs) have become a machine learning workhorse for screening the chemical space of crystalline materials in fields such as catalysis and energy storage, by predicting properties from structures.…

Graph Neural Networks (GNNs) are the subject of intense focus by the machine learning community for problems involving relational reasoning. GNNs can be broadly divided into spatial and spectral approaches. Spatial approaches use a form of…

Graph neural networks are prominent models for representation learning over graph-structured data. While the capabilities and limitations of these models are well-understood for simple graphs, our understanding remains incomplete in the…

Many real-world ubiquitous applications, such as parking recommendations and air pollution monitoring, benefit significantly from accurate long-term spatio-temporal forecasting (LSTF). LSTF makes use of long-term dependency between spatial…

Trajectory prediction plays a vital role in automotive radar systems, facilitating precise tracking and decision-making in autonomous driving. Generative adversarial networks with the ability to learn a distribution over future trajectories…

Spatio-temporal processes often exhibit highly heterogeneous and non-intuitive responses to localized disruptions, limiting the effectiveness of conventional message passing approaches in modeling local heterogeneity. We reformulate…

Graph neural networks (GNNs) are widely used as surrogates for costly experiments and first-principles simulations to study the behavior of compounds at atomistic scale, and their architectural complexity is constantly increasing to enable…

Under the second-order degenerate perturbation theory, we show that the physics of $N$ particles with arbitrary spin confined in a one dimensional trap in the strongly interacting regime can be described by super-exchange interaction. An…

We present a systematic derivation of effective lattice spin Hamiltonians derived from a rotationally invariant multi-orbital Hubbard model including a term ensuring Hund's rule coupling. The Hamiltonians are derived down-folding the…

We propose a method for obtaining parsimonious decompositions of networks into higher order interactions which can take the form of arbitrary motifs.The method is based on a class of analytically solvable generative models, where vertices…

Telecommunication networks play a critical role in modern society. With the arrival of 5G networks, these systems are becoming even more diversified, integrated, and intelligent. Traffic forecasting is one of the key components in such a…

Recently, pretraining methods for the Graph Neural Networks (GNNs) have been successful at learning effective representations from unlabeled graph data. However, most of these methods rely on pairwise relations in the graph and do not…

Cardiac blood flow patterns contain rich information about disease severity and clinical interventions, yet current imaging and computational methods fail to capture underlying relational structures of coherent flow features. We propose a…

Single crystal inelastic neutron scattering data contain rich information about the structure and dynamics of a material. Yet the challenge of matching sophisticated theoretical models with large data volumes is compounded by computational…

Spatio-temporal traffic prediction is crucial in intelligent transportation systems. The key challenge of accurate prediction is how to model the complex spatio-temporal dependencies and adapt to the inherent dynamics in data. Traditional…

Graph convolutional networks (GCNs) are a family of neural network models that perform inference on graph data by interleaving vertex-wise operations and message-passing exchanges across nodes. Concerning the latter, two key questions…

In traffic forecasting, graph convolutional networks (GCNs), which model traffic flows as spatio-temporal graphs, have achieved remarkable performance. However, existing GCN-based methods heuristically define the graph structure as the…

Inferring the laws of interaction between particles and agents in complex dynamical systems from observational data is a fundamental challenge in a wide variety of disciplines. We propose a non-parametric statistical learning approach to…

This paper proposes a knowledge-and-data-driven graph neural network-based collaboration learning model for reliable aircraft recognition in a heterogeneous radar network. The aircraft recognizability analysis shows that: (1) the semantic…

Spatio-temporal graph neural networks (ST-GNNs) have achieved notable success in structured domains such as road traffic and public transportation, where spatial entities can be naturally represented as fixed nodes. In contrast, many…