Augmenting and Tuning Knowledge Graph Embeddings

07/01/2019
by   Robert Bamler, et al.
0

Knowledge graph embeddings rank among the most successful methods for link prediction in knowledge graphs, i.e., the task of completing an incomplete collection of relational facts. A downside of these models is their strong sensitivity to model hyperparameters, in particular regularizers, which have to be extensively tuned to reach good performance [Kadlec et al., 2017]. We propose an efficient method for large scale hyperparameter tuning by interpreting these models in a probabilistic framework. After a model augmentation that introduces per-entity hyperparameters, we use a variational expectation-maximization approach to tune thousands of such hyperparameters with minimal additional cost. Our approach is agnostic to details of the model and results in a new state of the art in link prediction on standard benchmark data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/04/2022

KGLM: Integrating Knowledge Graph Structure in Language Models for Link Prediction

The ability of knowledge graphs to represent complex relationships at sc...
research
07/01/2022

Assessing the Effects of Hyperparameters on Knowledge Graph Embedding Quality

Embedding knowledge graphs into low-dimensional spaces is a popular meth...
research
03/19/2022

Sequence-to-Sequence Knowledge Graph Completion and Question Answering

Knowledge graph embedding (KGE) models represent each entity and relatio...
research
10/25/2021

A Probabilistic Framework for Knowledge Graph Data Augmentation

We present NNMFAug, a probabilistic framework to perform data augmentati...
research
07/11/2022

Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph Embeddings

Knowledge graph embedding (KGE) models are an effective and popular appr...
research
07/05/2017

Complex and Holographic Embeddings of Knowledge Graphs: A Comparison

Embeddings of knowledge graphs have received significant attention due t...
research
05/02/2019

Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications

Representing entities and relations in an embedding space is a well-stud...

Please sign up or login with your details

Forgot password? Click here to reset