Neural Probabilistic Logic Learning for Knowledge Graph Reasoning

TL;DR

Knowledge graph reasoning faces a trade-off between interpretability and scalability. The paper introduces Neural Probabilistic Logic Learning (NPLL), which integrates Markov Logic Networks with neural embeddings via a scoring module and variational inference, enabling efficient inference on large KGs. The method optimizes an ELBO by alternately updating an approximate posterior $Q(U)$ (E-step) and rule weights $\boldsymbol{\omega}$ (M-step), using a neural scorer to produce $p_k$ for facts and a bilinear-tensor scoring function $g(l,e_h,e_t)$ to drive downstream probabilities. Empirical results on four benchmarks show strong performance, data efficiency, and zero-shot capabilities, with notably compact model size compared to prior large-rule hybrids. The work demonstrates that principled probabilistic logic, when coupled with neural representations, can achieve high-quality KG reasoning with practical scalability and generalization to long-tail relations.

Abstract

Knowledge graph (KG) reasoning is a task that aims to predict unknown facts based on known factual samples. Reasoning methods can be divided into two categories: rule-based methods and KG-embedding based methods. The former possesses precise reasoning capabilities but finds it challenging to reason efficiently over large-scale knowledge graphs. While gaining the ability to reason over large-scale knowledge graphs, the latter sacrifices reasoning accuracy. This paper aims to design a reasoning framework called Neural Probabilistic Logic Learning(NPLL) that achieves accurate reasoning on knowledge graphs. Our approach introduces a scoring module that effectively enhances the expressive power of embedding networks, striking a balance between model simplicity and reasoning capabilities. We improve the interpretability of the model by incorporating a Markov Logic Network based on variational inference. We empirically evaluate our approach on several benchmark datasets, and the experimental results validate that our method substantially enhances the accuracy and quality of the reasoning results.

Figures (2)

• Figure 1: Visualization of Neural Probabilistic Logic Learning (NPLL)
• Figure 2: Performance of KG completion vs sparsity ratio