Mixture Policy based Multi-Hop Reasoning over N-tuple Temporal Knowledge Graphs
Temporal Knowledge Graphs (TKGs), which utilize quadruples in the form of (subject, predicate, object, timestamp) to describe temporal facts, have attracted extensive attention. N-tuple TKGs (N-TKGs) further extend traditional TKGs by utilizing n-tuples to incorporate auxiliary elements alongside core elements (i.e., subject, predicate, and object) of facts, so as to represent them in a more fine-grained manner. Reasoning over N-TKGs aims to predict potential future facts based on historical ones. However, existing N-TKG reasoning methods often lack explainability due to their black-box nature. Therefore, we introduce a new Reinforcement Learning-based method, named MT-Path, which leverages the temporal information to traverse historical n-tuples and construct a temporal reasoning path. Specifically, in order to integrate the information encapsulated within n-tuples, i.e., the entity-irrelevant information within the predicate, the information about core elements, and the complete information about the entire n-tuples, MT-Path utilizes a mixture policy-driven action selector, which bases on three low-level policies, namely, the predicate-focused policy, the core-element-focused policy and the whole-fact-focused policy. Further, MT-Path utilizes an auxiliary element-aware GCN to capture the rich semantic dependencies among facts, thereby enabling the agent to gain a deep understanding of each n-tuple. Experimental results demonstrate the effectiveness and the explainability of MT-Path.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge GraphsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Cast a Wider Net: Coordinated Pass@K Policy Optimization for Code Reasoning
Repeated sampling with a verifier is the standard way to allocate test-time compute for code generation, with pass@$K$ as the canonical metric. Yet the standard policy class draws $K$ independent samples from a single an…
Code GenerationParallel processor scheduling: formulation as multi-objective linguistic optimization and solution using Perceptual Reasoning based methodology
In the era of Industry 4.0, the focus is on the minimization of human element and maximizing the automation in almost all the industrial and manufacturing establishments. These establishments contain numerous processing …
SchedulingReasoning about Explanations for Negative Query Answers in DL-Lite
In order to meet usability requirements, most logic-based applications provide explanation facilities for reasoning services. This holds also for Description Logics, where research has focused on the explanation of both …
Policy Bifurcation in Safe Reinforcement Learning
Safe reinforcement learning (RL) offers advanced solutions to constrained optimal control problems. Existing studies in safe RL implicitly assume continuity in policy functions, where policies map states to actions in a …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement LearningImproving Arithmetic Reasoning Ability of Large Language Models through Relation Tuples, Verification and Dynamic Feedback
Current representations used in reasoning steps of large language models can mostly be categorized into two main types: (1) natural language, which is difficult to verify; and (2) non-natural language, usually programmin…
Arithmetic ReasoningRelation