Ministry of Testing

Testing data quality effectively

In some ways, data and its quality can seem strange to people used to assessing the quality of software. There’s often no observable behaviour to check and little in the way of structure to help you ...
GitHub

MoDiff - Graph Generation with Motif-Aware Diffusion Model

The subgraphs for training are preprocessed with motif detection and stored in different files in this code. We provide StackOverflow as an example. The 1h scale can be used directly, while the 5h and ...
GitHub

Multimodal Emotion Recognition in Conversations via Graph Structure Learning

Python 3.10.13 PyTorch 1.13.0 torch_geometric 2.5.2 torch-cluster 1.6.1 torch-scatter 2.1.1 torch-sparse 0.6.17 torch-spline-conv 1.2.2 sparsemax 0.1.9 CUDA 11.7 Train RIGSL using the MELD dataset.
IEEE

Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data

Abstract: Graph-based methods have demonstrated exceptional performance in semi-supervised classification. However, existing graph-based methods typically construct either a predefined graph in the ...
IEEE

Rethinking Unsupervised Graph Anomaly Detection With Deep Learning: Residuals and Objectives

Abstract: Anomalies often occur in real-world information networks/graphs, such as malevolent users in online review networks and fake news in social media. When representing such structured network ...