Mixture Policy based Multi-Hop Reasoning over N-tuple Temporal Knowledge Graphs

• URL: http://arxiv.org/abs/2505.12788v1
• Date: Mon, 19 May 2025 07:20:33 GMT
• Title: Mixture Policy based Multi-Hop Reasoning over N-tuple Temporal Knowledge Graphs
• Authors: Zhongni Hou, Miao Su, Xiaolong Jin, Zixuan Li, Long Bai, Jiafeng Guo, Xueqi Cheng,
• Abstract summary: 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.<n> Experimental results demonstrate the effectiveness and the explainability of MT-Path.
• Score: 67.52353093086151
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• A Survey of Link Prediction in N-ary Knowledge Graphs [70.45498073833213]
  N-ary Knowledge Graphs (NKGs) are a specialized type of knowledge graph designed to efficiently represent complex real-world facts.<n>Link prediction in NKGs aims to predict missing elements within these n-ary facts.<n>This paper presents the first comprehensive survey of link prediction in NKGs.
  arXiv  Detail & Related papers  (2025-06-10T16:44:27Z)
• Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning [87.10396098919013]
  Large Language Models (LLMs) have demonstrated extensive knowledge and remarkable proficiency in temporal reasoning.<n>We propose a Large Language Models-guided Dynamic Adaptation (LLM-DA) method for reasoning on Temporal Knowledge Graphs.<n>LLM-DA harnesses the capabilities of LLMs to analyze historical data and extract temporal logical rules.
  arXiv  Detail & Related papers  (2024-05-23T04:54:37Z)
• FecTek: Enhancing Term Weight in Lexicon-Based Retrieval with Feature Context and Term-level Knowledge [54.61068946420894]
  We introduce an innovative method by introducing FEature Context and TErm-level Knowledge modules. To effectively enrich the feature context representations of term weight, the Feature Context Module (FCM) is introduced. We also develop a term-level knowledge guidance module (TKGM) for effectively utilizing term-level knowledge to intelligently guide the modeling process of term weight.
  arXiv  Detail & Related papers  (2024-04-18T12:58:36Z)
• A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects [73.44022660932087]
  temporal characteristics are prominently evident in a substantial volume of knowledge. The continuous emergence of new knowledge, the weakness of the algorithm for extracting structured information from unstructured data, and the lack of information in the source dataset are cited. The task of Temporal Knowledge Graph Completion (TKGC) has attracted increasing attention, aiming to predict missing items based on the available information.
  arXiv  Detail & Related papers  (2023-08-04T16:49:54Z)
• Meta-Learning Based Knowledge Extrapolation for Temporal Knowledge Graph [4.103806361930888]
  Temporal KGs (TKGs) extend traditional Knowledge Graphs by associating static triples with timestamps forming quadruples. We propose a Meta-Learning based Temporal Knowledge Graph Extrapolation (MTKGE) model, which is trained on link prediction tasks sampled from the existing TKGs. We show that MTKGE consistently outperforms both the existing state-of-the-art models for knowledge graph extrapolation.
  arXiv  Detail & Related papers  (2023-02-11T09:52:26Z)
• ECOLA: Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations [35.51427298619691]
  We study enhancing temporal knowledge embedding with textual data. We propose Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations (ECOLA) Experiments show that ECOLA significantly enhances temporal embedding models with up to 287% relative improvements regarding Hits@1 on the link prediction task.
  arXiv  Detail & Related papers  (2022-03-17T20:08:25Z)
• CokeBERT: Contextual Knowledge Selection and Embedding towards Enhanced Pre-Trained Language Models [103.18329049830152]
  We propose a novel framework named Coke to dynamically select contextual knowledge and embed knowledge context according to textual context. Our experimental results show that Coke outperforms various baselines on typical knowledge-driven NLP tasks. Coke can describe the semantics of text-related knowledge in a more interpretable form than the conventional PLMs.
  arXiv  Detail & Related papers  (2020-09-29T12:29:04Z)
• Message Passing Neural Processes [3.0969191504482247]
  We introduce Message Passing Neural Processes (MPNPs), which explicitly makes use of relational structure within the model. MPNPs thrive at lower sampling rates, on existing benchmarks and newly-proposed CA and Cora-Branched tasks. We report strong generalisation over density-based CA rulesets and significant gains in challenging arbitrary-labelling and few-shot learning setups.
  arXiv  Detail & Related papers  (2020-09-29T09:40:09Z)

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.