Scaling Knowledge Graph Embedding Models

01/08/2022
by   Nasrullah Sheikh, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/11/2021

Multiple Run Ensemble Learning withLow-Dimensional Knowledge Graph Embeddings

Among the top approaches of recent years, link prediction using knowledg...
research
04/15/2021

Node Co-occurrence based Graph Neural Networks for Knowledge Graph Link Prediction

We introduce a novel embedding model, named NoKE, which aims to integrat...
research
07/29/2022

KG-NSF: Knowledge Graph Completion with a Negative-Sample-Free Approach

Knowledge Graph (KG) completion is an important task that greatly benefi...
research
05/25/2023

How to Turn Your Knowledge Graph Embeddings into Generative Models via Probabilistic Circuits

Some of the most successful knowledge graph embedding (KGE) models for l...
research
03/30/2022

AdaGrid: Adaptive Grid Search for Link Prediction Training Objective

One of the most important factors that contribute to the success of a ma...
research
12/19/2022

A Retrieve-and-Read Framework for Knowledge Graph Link Prediction

Knowledge graph (KG) link prediction aims to infer new facts based on ex...
research
10/16/2021

Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining

Improving the training and inference performance of graph neural network...

Please sign up or login with your details

Forgot password? Click here to reset