Scaling Knowledge Graph Embedding Models

8 Jan 2022  ·  Nasrullah Sheikh, Xiao Qin, Berthold Reinwald, Chuan Lei ·

Developing scalable solutions for training Graph Neural Networks (GNNs) for link prediction tasks is challenging due to the high data dependencies which entail high computational cost and huge memory footprint. We propose a new method for scaling training of knowledge graph embedding models for link prediction to address these challenges. Towards this end, we propose the following algorithmic strategies: self-sufficient partitions, constraint-based negative sampling, and edge mini-batch training. Both, partitioning strategy and constraint-based negative sampling, avoid cross partition data transfer during training. In our experimental evaluation, we show that our scaling solution for GNN-based knowledge graph embedding models achieves a 16x speed up on benchmark datasets while maintaining a comparable model performance as non-distributed methods on standard metrics.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.