Related papers: Accelerating 3D Non-LTE Synthesis with Graph Neura…

While deep learning (DL) architectures like convolutional neural networks (CNNs) have enabled effective solutions in image denoising, in general their implementations overly rely on training data, lack interpretability, and require tuning…

In recent years, tasks of machine learning ranging from image processing & audio/video analysis to natural language understanding have been transformed by deep learning. The data content in all these scenarios are expressed via Euclidean…

Nuclei classification is a critical step in computer-aided diagnosis with histopathology images. In the past, various methods have employed graph neural networks (GNN) to analyze cell graphs that model inter-cell relationships by…

Unsupervised graph anomaly detection aims at identifying rare patterns that deviate from the majority in a graph without the aid of labels, which is important for a variety of real-world applications. Recent advances have utilized Graph…

Mesh-based Graph Neural Networks (GNNs) have recently shown capabilities to simulate complex multiphysics problems with accelerated performance times. However, mesh-based GNNs require a large number of message-passing (MP) steps and suffer…

The development of robust Document AI models has been constrained by limited access to high-quality, labeled datasets, primarily due to data privacy concerns, scarcity, and the high cost of manual annotation. Traditional methods of…

Graph Neural Network (GNN) models on streaming graphs entail algorithmic challenges to continuously capture its dynamic state, as well as systems challenges to optimize latency, memory, and throughput during both inference and training. We…

Context. Three-dimensional non-local thermodynamical equilibrium (NLTE) radiative transfer calculations are a fundamental tool for a detailed spectral analysis in stellar atmospheres, but require vast amounts of computer power. This…

Graph Transformers have recently attracted attention for molecular property prediction by combining the inductive biases of graph neural networks (GNNs) with the global receptive field of Transformers. However, many existing hybrid…

Graph Neural Networks (GNNs) generalize neural networks from applications on regular structures to applications on arbitrary graphs, and have shown success in many application domains such as computer vision, social networks and chemistry.…

Graph Neural Networks (GNNs) have achieved remarkable success by extending traditional convolution to learning on non-Euclidean data. The key to the GNNs is adopting the neural message-passing paradigm with two stages: aggregation and…

Graph learning is currently dominated by graph kernels, which, while powerful, suffer some significant limitations. Convolutional Neural Networks (CNNs) offer a very appealing alternative, but processing graphs with CNNs is not trivial. To…

With the advent of Deep Learning (DL) techniques, especially Generative Adversarial Networks (GANs), data augmentation and generation are quickly evolving domains that have raised much interest recently. However, the DL techniques are data…

Photonic neural networks perform brain-inspired computations using photons instead of electrons that can achieve substantially improved computing performance. However, existing architectures can only handle data with regular structures,…

Most of the physical information about astrophysical objects is obtained via the analysis of their electromagnetic spectra. Observed data coupled with radiation transfer models in physical conditions representative of stars, planets,…

Increasing wireless network complexity demands scalable resource management. Classical GNNs excel at graph learning but incur high computational costs in large-scale settings. We present a fully quantum Graph Neural Network (QGNN) that…

This paper tackles the pressing challenge of mutagenicity prediction by introducing three ground-breaking approaches. First, it showcases the superior performance of 2D scattering coefficients extracted from molecular images, compared to…

Graph neural networks have achieved state-of-the-art accuracy for graph node classification. However, GNNs are difficult to scale to large graphs, for example frequently encountering out-of-memory errors on even moderate size graphs. Recent…

Implicit graph neural networks (IGNNs), which exhibit strong expressive power with a single layer, have recently demonstrated remarkable performance in capturing long-range dependencies (LRD) in underlying graphs while effectively…

One significant challenge of exploiting Graph neural networks (GNNs) in real-life scenarios is that they are always treated as black boxes, therefore leading to the requirement of interpretability. To address this, model-level…