Hardware-agnostic Computation for Large-scale Knowledge Graph Embeddings
This work solves scalability and usability problems for practitioners applying knowledge graph embeddings in real-world applications, though it is incremental as it builds on existing frameworks.
The paper tackles the challenge of scaling knowledge graph embedding frameworks to large graphs by developing a hardware-agnostic framework that addresses issues like distributed computation and continual learning, resulting in an open-source tool with pre-trained models exceeding 11.4 billion parameters.
Knowledge graph embedding research has mainly focused on learning continuous representations of knowledge graphs towards the link prediction problem. Recently developed frameworks can be effectively applied in research related applications. Yet, these frameworks do not fulfill many requirements of real-world applications. As the size of the knowledge graph grows, moving computation from a commodity computer to a cluster of computers in these frameworks becomes more challenging. Finding suitable hyperparameter settings w.r.t. time and computational budgets are left to practitioners. In addition, the continual learning aspect in knowledge graph embedding frameworks is often ignored, although continual learning plays an important role in many real-world (deep) learning-driven applications. Arguably, these limitations explain the lack of publicly available knowledge graph embedding models for large knowledge graphs. We developed a framework based on the frameworks DASK, Pytorch Lightning and Hugging Face to compute embeddings for large-scale knowledge graphs in a hardware-agnostic manner, which is able to address real-world challenges pertaining to the scale of real application. We provide an open-source version of our framework along with a hub of pre-trained models having more than 11.4 B parameters.