Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion

• URL: http://arxiv.org/abs/2109.09566v1
• Date: Thu, 16 Sep 2021 17:54:56 GMT
• Title: Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion
• Authors: Prithviraj Sen, Breno W. S. R. Carvalho, Ibrahim Abdelaziz, Pavan Kapanipathi, Francois Luus, Salim Roukos, Alexander Gray
• Abstract summary: We show that not all rule-based Knowledge Base Completion models are the same. We propose two distinct approaches that learn in one case: 1) a mixture of relations and the other 2) a mixture of paths. When implemented on top of neuro-symbolic AI, which learns rules by extending Boolean logic to real-valued logic, the latter model leads to superior KBC accuracy outperforming state-of-the-art rule-based KBC by 2-10% in terms of mean reciprocal rank.
• Score: 59.093293389123424
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent interest in Knowledge Base Completion (KBC) has led to a plethora of approaches based on reinforcement learning, inductive logic programming and graph embeddings. In particular, rule-based KBC has led to interpretable rules while being comparable in performance with graph embeddings. Even within rule-based KBC, there exist different approaches that lead to rules of varying quality and previous work has not always been precise in highlighting these differences. Another issue that plagues most rule-based KBC is the non-uniformity of relation paths: some relation sequences occur in very few paths while others appear very frequently. In this paper, we show that not all rule-based KBC models are the same and propose two distinct approaches that learn in one case: 1) a mixture of relations and the other 2) a mixture of paths. When implemented on top of neuro-symbolic AI, which learns rules by extending Boolean logic to real-valued logic, the latter model leads to superior KBC accuracy outperforming state-of-the-art rule-based KBC by 2-10% in terms of mean reciprocal rank. Furthermore, to address the non-uniformity of relation paths, we combine rule-based KBC with graph embeddings thus improving our results even further and achieving the best of both worlds.

Related papers

• ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning [107.61997887260056]
  We propose a novel framework, ChatRule, unleashing the power of large language models for mining logical rules over knowledge graphs. Specifically, the framework is initiated with an LLM-based rule generator, leveraging both the semantic and structural information of KGs. To refine the generated rules, a rule ranking module estimates the rule quality by incorporating facts from existing KGs.
  arXiv  Detail & Related papers  (2023-09-04T11:38:02Z)
• Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules [17.301284626706856]
  Methods of knowledge graph completion (KGC) can be classified into two major categories: rule-based reasoning and embedding-based reasoning. We propose a novel method that injects rules and learns representations iteratively to take full advantage of rules and embeddings.
  arXiv  Detail & Related papers  (2023-01-07T05:24:29Z)
• ZeroKBC: A Comprehensive Benchmark for Zero-Shot Knowledge Base Completion [54.898479917173]
  Knowledge base completion aims to predict the missing links in knowledge graphs. Previous KBC tasks mainly focus on the setting where all test entities and relations have appeared in the training set. We develop a comprehensive benchmark, ZeroKBC, that covers different possible scenarios of zero-shot KBC.
  arXiv  Detail & Related papers  (2022-12-06T16:02:09Z)
• RulE: Knowledge Graph Reasoning with Rule Embedding [69.31451649090661]
  We propose a principled framework called textbfRulE (stands for Rule Embedding) to leverage logical rules to enhance KG reasoning. RulE learns rule embeddings from existing triplets and first-order rules by jointly representing textbfentities, textbfrelations and textbflogical rules in a unified embedding space. Results on multiple benchmarks reveal that our model outperforms the majority of existing embedding-based and rule-based approaches.
  arXiv  Detail & Related papers  (2022-10-24T06:47:13Z)
• RelWalk A Latent Variable Model Approach to Knowledge Graph Embedding [50.010601631982425]
  This paper extends the random walk model (Arora et al., 2016a) of word embeddings to Knowledge Graph Embeddings (KGEs) We derive a scoring function that evaluates the strength of a relation R between two entities h (head) and t (tail) We propose a learning objective motivated by the theoretical analysis to learn KGEs from a given knowledge graph.
  arXiv  Detail & Related papers  (2021-01-25T13:31:29Z)
• MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning [46.68583750992613]
  We consider a generalized form of multi-hop rules, where each rule is a set of relation chains. We propose a two-step approach that first selects a small set of relation chains as a rule and then evaluates the confidence of the target relationship. Empirical results show that our multi-chain multi-hop (MCMH) rules result in superior results compared to the standard single-chain approaches.
  arXiv  Detail & Related papers  (2020-10-05T01:32:20Z)
• BoxE: A Box Embedding Model for Knowledge Base Completion [53.57588201197374]
  Knowledge base completion (KBC) aims to automatically infer missing facts by exploiting information already present in a knowledge base (KB) Existing embedding models are subject to at least one of the following limitations. BoxE embeds entities as points, and relations as a set of hyper-rectangles (or boxes)
  arXiv  Detail & Related papers  (2020-07-13T09:40:49Z)
• Building Rule Hierarchies for Efficient Logical Rule Learning from Knowledge Graphs [20.251630903853016]
  We propose new methods for pruning unpromising rules using rule hierarchies. We show that the application of HPMs is effective in removing unpromising rules.
  arXiv  Detail & Related papers  (2020-06-29T16:33:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.