Probability Calibration for Knowledge Graph Embedding Models

by   Pedro Tabacof, et al.

Knowledge graph embedding research has overlooked the problem of probability calibration. We show popular embedding models are indeed uncalibrated. That means probability estimates associated to predicted triples are unreliable. We present a novel method to calibrate a model when ground truth negatives are not available, which is the usual case in knowledge graphs. We propose to use Platt scaling and isotonic regression alongside our method. Experiments on three datasets with ground truth negatives show our contribution leads to well-calibrated models when compared to the gold standard of using negatives. We get significantly better results than the uncalibrated models from all calibration methods. We show isotonic regression offers the best the performance overall, not without trade-offs. We also show that calibrated models reach state-of-the-art accuracy without the need to define relation-specific decision thresholds.


Improving the Utility of Knowledge Graph Embeddings with Calibration

This paper addresses machine learning models that embed knowledge graph ...

Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes

Numeric values associated to edges of a knowledge graph have been used t...

A Physical Embedding Model for Knowledge Graphs

Knowledge graph embedding methods learn continuous vector representation...

LogicENN: A Neural Based Knowledge Graphs Embedding Model with Logical Rules

Knowledge graph embedding models have gained significant attention in AI...

ACTC: Active Threshold Calibration for Cold-Start Knowledge Graph Completion

Self-supervised knowledge-graph completion (KGC) relies on estimating a ...

Normalized Label Distribution: Towards Learning Calibrated, Adaptable and Efficient Activation Maps

The vulnerability of models to data aberrations and adversarial attacks ...

Battery Model Calibration with Deep Reinforcement Learning

Lithium-Ion (Li-I) batteries have recently become pervasive and are used...

Please sign up or login with your details

Forgot password? Click here to reset