LATENTLOGIC: Learning Logic Rules in Latent Space over Knowledge Graphs

Junnan Liu, Qianren Mao, Chenghua Lin, Yangqiu Song, Jianxin Li

Submission Type: Regular Short Paper

Submission Track: Machine Learning for NLP

Submission Track 2: Information Retrieval and Text Mining

Keywords: Knowledge Graph, Reasoning, Logic Rule

Abstract:

Learning logic rules for knowledge graph reasoning is essential as such rules provide interpretable explanations for reasoning and can be generalized to different domains.
However, existing methods often face challenges such as searching in a vast search space (e.g., enumeration of relational paths or multiplication of high-dimensional matrices) and inefficient optimization (e.g., techniques
based on reinforcement learning or EM algorithm).
To address these limitations, this paper proposes a novel framework called LatentLogic to efficiently mine logic rules by controllable generation in the latent space.
Specifically, to map the discrete relational paths into the latent space, we leverage a pre-trained VAE and employ a discriminator to establish an energy-based distribution.
Additionally, we incorporate a sampler based on ordinary differential equations, enabling the efficient generation of logic rules in our approach.
Extensive experiments on benchmark datasets demonstrate the effectiveness and efficiency of our proposed method.

Submission Number: 316