Reliable knowledge graph fact prediction via reinforcement learning
Abstract Knowledge graph (KG) fact prediction aims to complete a KG by determining the truthfulness of predicted triples. Reinforcement learning (RL)-based approaches have been widely used for fact prediction. However, the existing approaches largely suffer from unreliable calculations on rule confi...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-11-01
|
| Series: | Visual Computing for Industry, Biomedicine, and Art |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42492-023-00150-7 |
| _version_ | 1797454025656893440 |
|---|---|
| author | Fangfang Zhou Jiapeng Mi Beiwen Zhang Jingcheng Shi Ran Zhang Xiaohui Chen Ying Zhao Jian Zhang |
| author_facet | Fangfang Zhou Jiapeng Mi Beiwen Zhang Jingcheng Shi Ran Zhang Xiaohui Chen Ying Zhao Jian Zhang |
| author_sort | Fangfang Zhou |
| collection | DOAJ |
| description | Abstract Knowledge graph (KG) fact prediction aims to complete a KG by determining the truthfulness of predicted triples. Reinforcement learning (RL)-based approaches have been widely used for fact prediction. However, the existing approaches largely suffer from unreliable calculations on rule confidences owing to a limited number of obtained reasoning paths, thereby resulting in unreliable decisions on prediction triples. Hence, we propose a new RL-based approach named EvoPath in this study. EvoPath features a new reward mechanism based on entity heterogeneity, facilitating an agent to obtain effective reasoning paths during random walks. EvoPath also incorporates a new postwalking mechanism to leverage easily overlooked but valuable reasoning paths during RL. Both mechanisms provide sufficient reasoning paths to facilitate the reliable calculations of rule confidences, enabling EvoPath to make precise judgments about the truthfulness of prediction triples. Experiments demonstrate that EvoPath can achieve more accurate fact predictions than existing approaches. |
| first_indexed | 2024-03-09T15:31:18Z |
| format | Article |
| id | doaj.art-85a1823f8d934960bb6cd907b173ac98 |
| institution | Directory Open Access Journal |
| issn | 2524-4442 |
| language | English |
| last_indexed | 2024-03-09T15:31:18Z |
| publishDate | 2023-11-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Visual Computing for Industry, Biomedicine, and Art |
| spelling | doaj.art-85a1823f8d934960bb6cd907b173ac982023-11-26T12:14:57ZengSpringerOpenVisual Computing for Industry, Biomedicine, and Art2524-44422023-11-016111410.1186/s42492-023-00150-7Reliable knowledge graph fact prediction via reinforcement learningFangfang Zhou0Jiapeng Mi1Beiwen Zhang2Jingcheng Shi3Ran Zhang4Xiaohui Chen5Ying Zhao6Jian Zhang7School of Computer Science and Engineering, Central South UniversitySchool of Computer Science and Engineering, Central South UniversitySchool of Computer Science and Engineering, Central South UniversitySchool of Computer Science and Engineering, Central South UniversitySchool of Target and Data, Information Engineering UniversitySchool of Target and Data, Information Engineering UniversitySchool of Computer Science and Engineering, Central South UniversitySchool of Computer Science and Engineering, Central South UniversityAbstract Knowledge graph (KG) fact prediction aims to complete a KG by determining the truthfulness of predicted triples. Reinforcement learning (RL)-based approaches have been widely used for fact prediction. However, the existing approaches largely suffer from unreliable calculations on rule confidences owing to a limited number of obtained reasoning paths, thereby resulting in unreliable decisions on prediction triples. Hence, we propose a new RL-based approach named EvoPath in this study. EvoPath features a new reward mechanism based on entity heterogeneity, facilitating an agent to obtain effective reasoning paths during random walks. EvoPath also incorporates a new postwalking mechanism to leverage easily overlooked but valuable reasoning paths during RL. Both mechanisms provide sufficient reasoning paths to facilitate the reliable calculations of rule confidences, enabling EvoPath to make precise judgments about the truthfulness of prediction triples. Experiments demonstrate that EvoPath can achieve more accurate fact predictions than existing approaches.https://doi.org/10.1186/s42492-023-00150-7Knowledge graphFact predictionReinforcement learningEntity heterogeneityPostwalking mechanism |
| spellingShingle | Fangfang Zhou Jiapeng Mi Beiwen Zhang Jingcheng Shi Ran Zhang Xiaohui Chen Ying Zhao Jian Zhang Reliable knowledge graph fact prediction via reinforcement learning Visual Computing for Industry, Biomedicine, and Art Knowledge graph Fact prediction Reinforcement learning Entity heterogeneity Postwalking mechanism |
| title | Reliable knowledge graph fact prediction via reinforcement learning |
| title_full | Reliable knowledge graph fact prediction via reinforcement learning |
| title_fullStr | Reliable knowledge graph fact prediction via reinforcement learning |
| title_full_unstemmed | Reliable knowledge graph fact prediction via reinforcement learning |
| title_short | Reliable knowledge graph fact prediction via reinforcement learning |
| title_sort | reliable knowledge graph fact prediction via reinforcement learning |
| topic | Knowledge graph Fact prediction Reinforcement learning Entity heterogeneity Postwalking mechanism |
| url | https://doi.org/10.1186/s42492-023-00150-7 |
| work_keys_str_mv | AT fangfangzhou reliableknowledgegraphfactpredictionviareinforcementlearning AT jiapengmi reliableknowledgegraphfactpredictionviareinforcementlearning AT beiwenzhang reliableknowledgegraphfactpredictionviareinforcementlearning AT jingchengshi reliableknowledgegraphfactpredictionviareinforcementlearning AT ranzhang reliableknowledgegraphfactpredictionviareinforcementlearning AT xiaohuichen reliableknowledgegraphfactpredictionviareinforcementlearning AT yingzhao reliableknowledgegraphfactpredictionviareinforcementlearning AT jianzhang reliableknowledgegraphfactpredictionviareinforcementlearning |