graph neural networks

TFS: Tile-Aware SpMM–GeMM Fusion for Accelerating GNN Inference on Intel AMX

TFS is presented, a tile-aware fusion framework that eliminates this intermediate materialization by fusing SpMM and GeMM directly inside the tile registers of Intel’s Advanced Matrix Extensions (AMX).

Early Bearing Fault Evolution Modeling with a Dynamics-Constrained Graph Neural Network

During the incipient localized-fault stage, impact signatures in ball bearings are weak. Accurate degradation labels are difficult to construct. Purely data-driven models often lack physical consistency. To address these issues, a dynamics-constrained graph neural network (DC-GNN) was developed for early fault evolutio...

Beyond Structural Representations: A Semantic-Relational Graph Neural Network for Polypharmacy Side Effect Prediction.

Artificial intelligence for weather and climate: a survey of methods, benchmarks, and scientific machine learning challenges

Weather and climate science is a uniquely demanding testbed for artificial intelligence, combining petabyte-scale spatiotemporal complex data on a rotating sphere, governing partial differential equations coupled to global observational and reanalysis archives, climate non-stationarity that distinguishes it from statio...

A Public Canvas Course - Cybertraining for Chemical Data scientists

We present a free public Canvas course connects machine learning concepts with chemical applications, including Python examples and quizzes. The course is available at https://notredamecatalog.instructure.com/courses/21946~1257. The course also includes three animation videos that introduce neural networks, random fore...

Graph Neural Networks for Spatio-Temporal Threat Detection in UAV Swarms

AI-Powered Cybersecurity: Emerging Trends and Challenges – A Narrative Review

This study is driven by the fact that artificial intelligence (AI) technologies are quickly changing the landscape of intrusion detection, malware analysis and mitigation of advanced cyber-attacks making cybersecurity a domain most impacted by this revolution. In order to provide an objective overview on AI uses in cyb...

Decoding Parkinson's Disease from EEG Signals: A Systematic Review of Machine Learning and Deep Learning Frameworks

Parkinson's disease (PD) is the second most common neurodegenerative disorder worldwide, yet it continues to be diagnosed primarily through subjective clinical evaluation - a process that is slow, inconsistent across observers, and largely blind to early-stage disease. This paper reviews some studies published between...

Development of deep learning methods for efficient exploration of ultra-large chemical spaces

The exponential growth of synthetically accessible chemical libraries, now exceeding tens of billions of molecules, creates unprecedented opportunities for drug discovery alongside formidable computational challenges. Conventional structure-based virtual screening such as docking, though foundational, struggles to scal...

Construction of Soliton and Lump Solutions for (2+1)-dimensional CBS Equation and EGPINN-based Numerical Learning

Code and data for HDSTAR-GNN: A heterogeneous dynamic spatiotemporal graph neural network model for quantifying spatially cascading impacts of extreme precipitation on economic growth

Dynamic spatiotemporal autoregressive models explicitly represent spatial dependency and temporal dynamics underlying an evolving spatial system, providing a natural framework for investigating how climate shocks propagate, persist, and amplify. Yet their application to fine-resolution climate-impact assessment is crit...

Machine Learning‐Driven Design of Electrolytes and Interfaces for Solid‐State Lithium Batteries: Progress and Outlook

Solid‐state lithium batteries are a leading candidate for next‐generation high‐energy‐density and high‐safety batteries but suffer from inherent trade‐offs among ionic conductivity, electrochemical stability, and mechanical strength in solid‐state electrolytes, as well as complex electrode–electrolyte interfacial cou...