Cyclical Training Framework with Graph Feature Optimization for Knowledge Graph Reasoning  

作　　者：Xiaotong Han Yunqi Jiang Haitao Wang Yuan Tian 

机构地区：[1]School of Artificial Intelligence,Jilin University,Changchun,130012,China [2]Engineering Research Center of Knowledge-Driven Human-Machine Intelligence,MOE,Changchun,130012,China [3]College of Computer Science and Technology,Jilin University,Changchun,130012,China

出　　处：《Computers, Materials & Continua》2025年第5期1951-1971,共21页计算机、材料和连续体(英文)

基　　金：supported by the National Key Research and Development Program of China(No.2023YFF0905400);the National Natural Science Foundation of China(No.U2341229).

摘　　要：Knowledge graphs(KGs),which organize real-world knowledge in triples,often suffer from issues of incompleteness.To address this,multi-hop knowledge graph reasoning(KGR)methods have been proposed for interpretable knowledge graph completion.The primary approaches to KGR can be broadly classified into two categories:reinforcement learning(RL)-based methods and sequence-to-sequence(seq2seq)-based methods.While each method has its own distinct advantages,they also come with inherent limitations.To leverage the strengths of each method while addressing their weaknesses,we propose a cyclical training method that alternates for several loops between the seq2seq training phase and the policy-based RL training phase using a transformer architecture.Additionally,a multimodal data encoding(MDE)module is introduced to improve the representation of entities and relations in KGs.TheMDE module treats entities and relations as distinct modalities,processing each with a dedicated network specialized for its respective modality.It then combines the representations of entities and relations in a dynamic and fine-grained manner using a gating mechanism.The experimental results from the knowledge graph completion task highlight the effectiveness of the proposed framework.Across five benchmark datasets,our framework achieves an average improvement of 1.7%in the Hits@1 metric and a 0.8%average increase in the Mean Reciprocal Rank(MRR)compared to other strong baseline methods.Notably,the maximum improvement in Hits@1 exceeds 4%,further demonstrating the effectiveness of the proposed approach.

关 键 词：Knowledge graph reinforcement learning TRANSFORMER 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]