A Hybrid Model for Learning Embeddings and Logical Rules Simultaneously from Knowledge Graphs

TL;DR

This paper introduces a hybrid approach that simultaneously learns logical rules and embeddings for knowledge graphs, leveraging their complementary strengths to improve reasoning, especially in sparse data scenarios.

Contribution

It proposes a novel cross feedback hybrid model that jointly learns rules and embeddings, enhancing knowledge graph reasoning beyond existing standalone methods.

Findings

Outperforms other methods on benchmark datasets

Effective in sparse knowledge graph settings

Shows improved reasoning accuracy with hybrid approach

Abstract

The problem of knowledge graph (KG) reasoning has been widely explored by traditional rule-based systems and more recently by knowledge graph embedding methods. While logical rules can capture deterministic behavior in a KG they are brittle and mining ones that infer facts beyond the known KG is challenging. Probabilistic embedding methods are effective in capturing global soft statistical tendencies and reasoning with them is computationally efficient. While embedding representations learned from rich training data are expressive, incompleteness and sparsity in real-world KGs can impact their effectiveness. We aim to leverage the complementary properties of both methods to develop a hybrid model that learns both high-quality rules and embeddings simultaneously. Our method uses a cross feedback paradigm wherein, an embedding model is used to guide the search of a rule mining system to mine rules and infer new facts. These new facts are sampled and further used to refine the embedding model. Experiments on multiple benchmark datasets show the effectiveness of our method over other competitive standalone and hybrid baselines. We also show its efficacy in a sparse KG setting and finally explore the connection with negative sampling.