graph neural networks

A MACHINE LEARNING SURROGATE FOR ALPINE3D SNOWPACK SIMULATION: PERSISTENCE-BASED EVALUATION AND A PATH TOWARD SNOWDRIFT

Distributed snow-cover models such as Alpine3D and SNOWPACK provide spatially detailed information on snowpack evolution, surface energy balance, and terrain-driven variability that is relevant to avalanche operations.The drawback is the computational cost of high-resolution, multiseason simulations, which limits repea...

Graph Convolutional Neural Networks Sensitivity Under Probabilistic Error Model (video)

The Drift Neural Network: A Neuro-Symbolic Cognitive Architecture for Autonomous Systems

The Drift Neural Network is a neuro-symbolic cognitive architecture that joins four faculties in one closed loop, offered against the prevailing bet on scaling the autoregressive transformer. A transformer produces output by statistical continuation over a fixed matrix of weights, and four of its limits are structural,...

Structured PREreview of "Training, learning and inference: unified dynamics of neural systems"

This Zenodo record is a permanently preserved version of a Structured PREreview. You can view the complete PREreview at https://prereview.org/reviews/22899514. Does the introduction explain the objective of the research presented in the preprint? Yes The introduction clearly establishes the motivation, core research ob...

Graph Convolutional Neural Networks Sensitivity Under Probabilistic Error Model (slides) - Slides

Graph Convolutional Neural Networks Sensitivity Under Probabilistic Error Model (slides) - Slides

Graph Convolutional Neural Networks Sensitivity Under Probabilistic Error Model (video)

CiteJustice: Automated Legal Judgment Prediction for Indian Courts Using Graph Neural Networks

CiteJustice is an automated legal judgment prediction framework designed for Indian courts. Unlike conventional approaches that rely primarily on semantic similarity between a new case and past judgments, CiteJustice incorporates the evolving authority of legal precedents through a Dynamic Precedent Evolution Graph (DP...

p–LSGR: A lightweight post–hoc latent–space resampling framework for imbalanced and complex graph distributions

Graph neural networks (GNNs) are widely used across domains but remain sensitive to class imbalance, class overlap, and complex data distributions, limiting reliability in real-world settings. Existing imbalance-mitigation strategies provide only partial robustness, are often computationally expensive, and leave post-h...

Hypergraph Neural Networks Approach for 3-Dimensional Matching Problem

Dynamic time-lagged relation graph structure learning for multivariate time series forecasting

TGCAE: temporal graph convolutional autoencoder for robust anomaly detection in object-centric process mining

With the deep integration of machine learning and cybernetics technologies in business process management (BPM), robust anomaly detection in object-centric process mining is crucial for enhancing operational efficiency and quality within enterprises. Existing anomaly detection approaches predominantly rely on flattened...