graph neural networks

A Review of the Applications of Artificial Intelligence in the Full-Process Design of Integrated Circuits

In the post-Moore era, traditional integrated circuit (IC) design faces bottlenecks such as long design cycles, high costs, and difficulty in PPA convergence. Artificial intelligence (AI), with its data-driven and global optimization capabilities, has pene trated the entire IC design process. This paper systematically...

Deviation-Based Graph Neural Networks with Kolmogorov-Arnold Transformations for Multiclass Alzheimer’s Disease Classification

Direction-Aware Heterogeneous Graph Neural Networks with Dual-Conditioned Normalizing Flows for Spatio-Temporal Anomaly Detection

Graph Neural Network Interpretation of Burst Initiation for In Silico Cortical Networks

Micro-video recommendation based on multi-dimensional sequence features in content e-commerce platform

Compared with traditional e-commerce platforms, content-based e-commerce has obvious advantages in commodity display, as it can present commodities more comprehensively, three-dimensionally and flexibly, providing better user service experience. However, the micro-video format of content-based e-commerce, with its comp...

Interaction-enhanced lane-change early warning in congested traffic: a spatial risk propagation-aware approach

This paper presents an interaction-enhanced Lane-Changing Early Warning (LCEW) system designed to issue reliable early warning signals through a spatial risk-propagation-aware approach. The system is built upon interpretable multi-vehicle trajectory predictions and collision risk identification within an extended LC zo...

Experiments on Multi-UAV Path Planning Using DRL Based on Graph Neural Networks

PruneInfer: Exact Full-Neighborhood GNN Inference of Large Datasets on a Single GPU via Full Topology Pruning

PruneInfer is the only system on the authors' experimental configuration that maintains accuracy comparable to full-graph inference across all evaluated models and achieves up to 4.49 × speedup over DGL and up to 7.05 × speedup over GDL-GNN across the evaluated datasets.

Memory-Aware Joint Optimisation of Partitioning and Scheduling for Pipeline-Parallel Training

Pipeline parallelism (PP) is widely adopted for distributed training of neural networks, but its efficiency is limited by pipeline bubbles that leave devices idle. A variety of schedules have been proposed to reduce these bubbles, yet most are hand-crafted, rely on idealised timing assumptions as well as rigid structur...

AtomFlow: Accelerating GNN-Based Molecular Dynamics with ab initio Accuracy on Fugaku Supercomputer

This paper proposes AtomFlow, a holistic acceleration for a representative GNN-based MD model on the Fugaku supercomputer, and redesigns the inference workflow with a framework-free implementation to avoid the overhead of the PyTorch framework on Fugaku.

AGENTIC SOCIO-TECHNICAL SYSTEMS FOR AGING DEMOGRAPHICS: INTEGRATING GRAPH NEURAL NETWORKS AND DEEP REINFORCEMENT LEARNING FOR RESILIENT HEALTHCARE LOGISTICS

The fast-growing aging demographics in both developed and developing countries are exerting increasing stress on healthcare systems, especially those that experience high old-age dependency rates.Healthcare logistics models based on traditional methods tend to employ static and reactive decision-making strategies, whic...

Small Language Models as Graph Classifiers: Evaluating and Improving Permutation Robustness