GitHub

A production-ready implementation of Graph Few-Shot Learning using Prototypical Networks with Graph Neural Networks (GCN and GAT).

This project implements few-shot learning on graph-structured data, where the goal is to learn from very few labeled examples per class. It combines Graph Neural Networks with Prototypical Networks to ...
GitHub

bamarler/Defect-GNN-cpp

Implements Fang & Yan's methodology: crystal structures → graph representations where atoms are nodes (with learned element embeddings) and edges encode interatomic distances via Gaussian radial basis ...
IEEE

Expert Recommendation System for Project Reviews Based on Knowledge Graphs

Abstract: In scientific research projects or technical evaluations, finding suitable reviewers is crucial. However, traditional methods often rely on simple keyword matching or manual selection, ...
IEEE

Design and Implementation of Multi-Agent Systems: A Lang Graph-Based Approach

Abstract: A paradigm known as multi-agent systems (MAS) combines several independent agents to accomplish intricate tasks. The creation of such systems presents difficulties with control flow, ...