Benchmarking Recommendation, Classification, and Tracing Based on Hugging Face Knowledge Graph
Authors:
Preprint
Abstract
The rapid growth of open source machine learning (ML) resources, such as models and datasets, has accelerated IR research. However, existing platforms like Hugging Face do not explicitly utilize structured representations, limiting advanced queries and analyses such as tracing model evolution and recommending relevant datasets. To fill the gap, we construct HuggingKG, the first large-scale knowledge graph built from the Hugging Face community for ML resource management. With 2.6 million nodes and 6.2 million edges, HuggingKG captures domain-specific relations and rich textual attributes. It enables us to further present HuggingBench, a multi-task benchmark with three novel test collections for IR tasks including resource recommendation, classification, and tracing. Our experiments reveal unique characteristics of HuggingKG and the derived tasks. Both resources are publicly available, expected to advance research in open source resource sharing and management.Keywords
All Related Versions
- Version 1, 2025-05-23, ArXiv
- Published version: , 3433.
This publication has 32 references indexed in Scilit:
- A large-scale audit of dataset licensing and attribution in AINature Machine Intelligence, 2024
- Improving Issue-PR Link Prediction via Knowledge-Aware Heterogeneous Graph LearningIEEE Transactions on Software Engineering, 2024
- Personalized Repository Recommendation Service for Developers with Multi-modal Features Learning2023
- Task-Oriented ML/DL Library Recommendation Based on a Knowledge GraphIEEE Transactions on Software Engineering, 2023
- LightGCN2020
- paper2repo: GitHub Repository Recommendation for Academic Papers2020
- Dataset search: a surveyThe VLDB Journal, 2019
- OAG2019
- GRETA: Graph-Based Tag Assignment for GitHub Repositories2016
- WikidataCommunications of the ACM, 2014