This repository contains baseline code for the KG-to-KG Semantic Similarity benchmark dataset:

The code preserves the original baseline pipeline:

The original scripts expect legacy local input folders such as:

The Hugging Face dataset stores the same graph pairs as Parquet files. Run the materialization script first to recreate the legacy folders from the dataset repository.

This downloads seungryeol-22/KG-to-KG-Semantic-Similarity and creates:

Run a scoring script:

Then run ranking:

Then run metrics:

Results are written by the original scripts under Result/ and Metric_Results/.

Install the packages needed by the baseline you plan to run. The adapter requires:

Graph-kernel baselines require:

SBERT baseline requires:

KGE and InGram baselines require PyTorch-related dependencies such as torch, torch-geometric, scipy, scikit-learn, and igraph.

Paper: https://arxiv.org/abs/2606.29180

Dataset: https://huggingface.co/datasets/seungryeol-22/KG-to-KG-Semantic-Similarity

Code source: https://github.com/SeungRyeolBaek/KG-to-KG-Semantic-Similarity