{"type":"ScholarlyArticle","title":"Soft Reasoning Paths for Knowledge Graph Completion","authors":[{"name":"Yanning Hou","slug":"yanning-hou","given":"Yanning","family":"Hou","affiliation":"College of Intelligence Science and Technology , National University of Defense Technology , Changsha , China"},{"name":"Sihang Zhou","slug":"sihang-zhou","given":"Sihang","family":"Zhou","affiliation":"College of Intelligence Science and Technology , National University of Defense Technology , Changsha , China"},{"name":"Ke Liang","slug":"ke-liang","given":"Ke","family":"Liang","affiliation":"College of Computer Science and Technology , National University of Defense Technology , Changsha , China"},{"name":"Lingyuan Meng","slug":"lingyuan-meng","given":"Lingyuan","family":"Meng","affiliation":"College of Computer Science and Technology , National University of Defense Technology , Changsha , China"},{"name":"Xiaoshu Chen","slug":"xiaoshu-chen","given":"Xiaoshu","family":"Chen","affiliation":"College of Computer Science and Technology , National University of Defense Technology , Changsha , China"},{"name":"Ke Xu","slug":"ke-xu","given":"Ke","family":"Xu","affiliation":"School of Artifcial Intelligence , Anhui University , Hefei , China"},{"name":"Siwei Wang","slug":"siwei-wang","given":"Siwei","family":"Wang","affiliation":"College of Computer Science and Technology , National University of Defense Technology , Changsha , China"},{"name":"Xinwang Liu","slug":"xinwang-liu","given":"Xinwang","family":"Liu","affiliation":"College of Computer Science and Technology , National University of Defense Technology , Changsha , China"},{"name":"Jian Huang","slug":"jian-huang","given":"Jian","family":"Huang","affiliation":"College of Intelligence Science and Technology , National University of Defense Technology , Changsha , China"}],"abstract":"Reasoning paths are reliable information in knowledge graph completion (KGC) in which algorithms can find strong clues of the actual relation between entities. However, in real-world applications, it is difficult to guarantee that computationally affordable paths exist toward all candidate entities. According to our observation, the prediction accuracy drops significantly when paths are absent. To make the proposed algorithm more stable against the missing path circumstances, we introduce soft reasoning paths. Concretely, a specific learnable latent path embedding is concatenated to each relation to help better model the characteristics of the corresponding paths. The combination of the relation and the corresponding learnable embedding is termed a soft path in our paper. By aligning the soft paths with the reasoning paths, a learnable embedding is guided to learn a generalized path representation of the corresponding relation. In addition, we introduce a hierarchical ranking strategy to make full use of information about the entity, relation, path, and soft path to help improve both the efficiency and accuracy of the model. Extensive experimental results illustrate that our algorithm outperforms the compared state-of-the-art algorithms by a notable margin. Our code will be released at https://github.com/7HHHHH/SRP-KGC.","doi":"10.24963/ijcai.2025/327","url":"https://ijcai.org/proceedings/2025/327","pdf":"https://ijcai.org/proceedings/2025/0327.pdf","markdown":"https://ijcai.org/proceedings/2025/327.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/327","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Data Mining","track":"Main Track","number":327,"pages":{"first":2937,"last":2945},"keywords":["Data Mining: DM: Knowledge graphs and knowledge base completion","Knowledge Representation and Reasoning: KRR: Applications","Knowledge Representation and Reasoning: KRR: Learning and reasoning"],"videos":[],"references":[{"position":1,"raw":"[Balazevic et al., 2019] Ivana Balazevic, Carl Allen, and Timothy M. Hospedales. Tucker: Tensor factorization for knowledge graph completion. In Proceedings of the 2019 Conference on Empirical Methods in Natural Lan- guage Processing and the 9th International Joint Confer- ence on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019. Associa- tion for Computational Linguistics, 2019.","title":"Tucker: Tensor factorization for knowledge graph completion","authors":"Ivana Balazevic, Carl Allen, Timothy M Hospedales","year":"2019","venue":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bordes et al., 2013] Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Weston, and Oksana Yakhnenko. Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neu- ral Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States, 2013.","title":"Translating embeddings for modeling multi-relational data","authors":"Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Weston, Oksana Yakhnenko","year":"2013","venue":"Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2020] Ting Chen, Simon Kornblith, Moham- mad Norouzi, and Geoffrey E. Hinton. A simple frame- work for contrastive learning of visual representations. ArXiv, abs/2002.05709, 2020.","title":"A simple framework for contrastive learning of visual representations","authors":"Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E Hinton","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2022] Chen Chen, Yufei Wang, Bing Li, and Kwok-Yan Lam. Knowledge is flat: A seq2seq genera- tive framework for various knowledge graph completion. In Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Re- public of Korea, October 12-17, 2022. International Com- mittee on Computational Linguistics, 2022.","title":"Knowledge is flat: A seq2seq generative framework for various knowledge graph completion","authors":"Chen Chen, Yufei Wang, Bing Li, Kwok-Yan Lam","year":"2022","venue":"Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2023] Chen Chen, Yufei Wang, Aixin Sun, Bing Li, and Kwok-Yan Lam. Dipping plms sauce: Bridg- ing structure and text for effective knowledge graph com- pletion via conditional soft prompting. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023. Association for Com- putational Linguistics, 2023.","title":"Dipping plms sauce: Bridging structure and text for effective knowledge graph completion via conditional soft prompting","authors":"Chen Chen, Yufei Wang, Aixin Sun, Bing Li, Kwok-Yan Lam","year":"2023","venue":"Findings of the Association for Computational Linguistics: ACL 2023","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dettmers et al., 2017] Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, and Sebastian Riedel. Convolutional 2d knowledge graph embeddings. In AAAI Conference on Ar- tificial Intelligence, 2017.","title":"Convolutional 2d knowledge graph embeddings","authors":"Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel","year":"2017","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dinan et al., 2019] Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. Wizard of wikipedia: Knowledge-powered conversational agents. In 7th International Conference on Learning Rep- resentations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net, 2019.","title":"Wizard of wikipedia: Knowledge-powered conversational agents","authors":"Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, Jason Weston","year":"2019","venue":"7th International Conference on Learning Representations, ICLR 2019","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Edge et al., 2024] Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Tru- itt, and Jonathan Larson. From local to global: A graph rag approach to query-focused summarization. ArXiv, abs/2404.16130, 2024.","title":"From local to global: A graph rag approach to query-focused summarization","authors":"Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Jonathan Larson","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Ge et al., 2023] Xiou Ge, Yun Cheng Wang, Bin Wang, and C.-C. Jay Kuo. Compounding geometric operations for knowledge graph completion. In Annual Meeting of the Association for Computational Linguistics, 2023.","title":"Compounding geometric operations for knowledge graph completion","authors":"Ge","year":"2023","venue":"Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Huang et al., 2018] Jin Huang, Wayne Xin Zhao, Hongjian Dou, Ji-Rong Wen, and Edward Y. Chang. Improv- ing sequential recommendation with knowledge-enhanced memory networks. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR 2018, Ann Arbor, MI, USA, July 08-12, 2018. ACM, 2018.","title":"Improving sequential recommendation with knowledge-enhanced memory networks","authors":"Jin Huang, Wayne Xin Zhao, Hongjian Dou, Ji-Rong Wen, Edward Y Chang","year":"2018","venue":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR 2018","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Iwamoto and Kameiwa, 2024] Yuki Iwamoto and Ken Kameiwa. Predicting from a different perspective in re- ranking model for inductive knowledge graph completion. ArXiv, abs/2405.16902, 2024.","title":"Predicting from a different perspective in reranking model for inductive knowledge graph completion","authors":"Yuki Iwamoto, Ken Kameiwa","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Khosla et al., 2020] Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. Supervised con- trastive learning. ArXiv, abs/2004.11362, 2020.","title":"Supervised contrastive learning","authors":"Khosla","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2022] Da Li, Boqing Zhu, Sen Yang, Kele Xu, Ming Yi, Yukai He, and Huaimin Wang. Multi-task pre- training language model for semantic network completion. ACM Trans. Asian Low Resour. Lang. Inf. Process., 2022.","title":"Multi-task pretraining language model for semantic network completion","authors":"Da Li, Boqing Zhu, Sen Yang, Kele Xu, Ming Yi, Yukai He, Huaimin Wang","year":"2022","venue":"ACM Trans. Asian Low Resour. Lang. Inf. Process","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2023] Rui Li, Xu Chen, Chaozhuo Li, Yanming Shen, Jianan Zhao, Yujing Wang, Weihao Han, Hao Sun, Weiwei Deng, Qi Zhang, and Xing Xie. To copy rather than memorize: A vertical learning paradigm for knowl- edge graph completion. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pages 6335-6347. Association for Com- putational Linguistics, 2023.","title":"To copy rather than memorize: A vertical learning paradigm for knowledge graph completion","authors":"Rui Li, Xu Chen, Chaozhuo Li, Yanming Shen, Jianan Zhao, Yujing Wang, Weihao Han, Hao Sun, Weiwei Deng, Qi Zhang, Xing Xie","year":"2023","venue":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lin et al., 2015] Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, and Song Liu. Modeling rela- tion paths for representation learning of knowledge bases. ArXiv, abs/1506.00379, 2015.","title":"Modeling relation paths for representation learning of knowledge bases","authors":"Lin","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Qiao et al., 2023] Zile Qiao, Wei Ye, Dingyao Yu, Tong Mo, Weiping Li, and Shikun Zhang. Improving knowledge graph completion with generative hard negative mining. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pages 5866- 5878. Association for Computational Linguistics, 2023.","title":"Improving knowledge graph completion with generative hard negative mining","authors":"Zile Qiao, Wei Ye, Dingyao Yu, Tong Mo, Weiping Li, Shikun Zhang","year":"2023","venue":"Findings of the Association for Computational Linguistics: ACL 2023","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Sun et al., 2019a] Haitian Sun, Tania Bedrax-Weiss, and William W. Cohen. Pullnet: Open domain question an- swering with iterative retrieval on knowledge bases and text. In Proceedings of the 2019 Conference on Empir- ical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019. Association for Computational Lin- guistics, 2019.","title":"Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text","authors":"Sun","year":"2019","venue":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sun et al., 2019b] Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. Rotate: Knowledge graph embed- ding by relational rotation in complex space. In 7th Inter- national Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019.","title":"Rotate: Knowledge graph embedding by relational rotation in complex space","authors":"Sun","year":"2019","venue":"7th International Conference on Learning Representations, ICLR 2019","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Tan et al., 2022] Zhaoxuan Tan, Zilong Chen, Shangbin Feng, Qingyue Zhang, Qinghua Zheng, Jundong Li, and Minnan Luo. Kracl: Contrastive learning with graph context modeling for sparse knowledge graph completion. Proceedings of the ACM Web Conference 2023, 2022.","title":"Kracl: Contrastive learning with graph context modeling for sparse knowledge graph completion","authors":"Tan","year":"2022","venue":"Proceedings of the ACM Web Conference 2023","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Teru et al., 2020] Komal K. Teru, Etienne G. Denis, and William L. Hamilton. Inductive relation prediction by sub- graph reasoning. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, volume 119 of Proceedings of Ma- chine Learning Research, pages 9448-9457. PMLR, 2020.","title":"Inductive relation prediction by subgraph reasoning","authors":"K Komal, Etienne G Teru, William L Denis, Hamilton","year":"2020","venue":"Proceedings of the 37th International Conference on Machine Learning, ICML 2020","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Trouillon et al., 2016] Théo Trouillon, Johannes Welbl, Se- bastian Riedel, Éric Gaussier, and Guillaume Bouchard. Complex embeddings for simple link prediction. ArXiv, abs/1606.06357, 2016.","title":"Complex embeddings for simple link prediction","authors":"Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, Guillaume Bouchard","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Vashishth et al., 2019] Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, and Partha Pratim Talukdar. Composition- based multi-relational graph convolutional networks. ArXiv, abs/1911.03082, 2019.","title":"Compositionbased multi-relational graph convolutional networks","authors":"Shikhar Vashishth, Soumya Sanyal, Nitin Vikram, Partha Pratim Talukdar","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2014] Zhen Wang, Jianwen Zhang, Jianlin Feng, and Zheng Chen. Knowledge graph embedding by translating on hyperplanes. In AAAI Conference on Artifi- cial Intelligence, 2014.","title":"Knowledge graph embedding by translating on hyperplanes","authors":"Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen","year":"2014","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2021] Bo Wang, Tao Shen, Guodong Long, Tianyi Zhou, Ying Wang, and Yi Chang. Structure- augmented text representation learning for efficient knowl- edge graph completion. In WWW '21: The Web Confer- ence 2021, Virtual Event / Ljubljana, Slovenia, April 19- 23, 2021. ACM / IW3C2, 2021.","title":"Structureaugmented text representation learning for efficient knowledge graph completion","authors":"Bo Wang, Tao Shen, Guodong Long, Tianyi Zhou, Ying Wang, Yi Chang","year":"2021","venue":"WWW '21: The Web Conference 2021, Virtual Event","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wang et al., 2022a] Liang Wang, Wei Zhao, Zhuoyu Wei, and Jingming Liu. Simkgc: Simple contrastive knowledge graph completion with pre-trained language models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022. Association for Computational Linguistics, 2022.","title":"Simkgc: Simple contrastive knowledge graph completion with pre-trained language models","authors":"Wang","year":"2022","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang et al., 2022b] Xintao Wang, Qianyu He, Jiaqing Liang, and Yanghua Xiao. Language models as knowl- edge embeddings. In Luc De Raedt, editor, Proceedings of the Thirty-First International Joint Conference on Arti- ficial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022. ijcai.org, 2022.","title":"Language models as knowledge embeddings","authors":"Wang","year":"2022","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022","doi":null,"url":null,"internal_url":"/proceedings/2022/318"},{"position":27,"raw":"[Xie et al., 2024] Zhiwen Xie, Yi Zhang, Guangyou Zhou, Jin Liu, Xinhui Tu, and Jimmy Xiangji Huang. One sub- graph for all: Efficient reasoning on opening subgraphs for inductive knowledge graph completion. IEEE Trans- actions on Knowledge and Data Engineering, 36:8914- 8927, 2024.","title":"One subgraph for all: Efficient reasoning on opening subgraphs for inductive knowledge graph completion","authors":"Zhiwen Xie, Yi Zhang, Guangyou Zhou, Jin Liu, Xinhui Tu, Jimmy Xiangji Huang","year":"2024","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yang et al., 2024] Rui Yang, Jiahao Zhu, Jianping Man, Hongze Liu, Li Fang, and Yi Zhou. Gs-kgc: A genera- tive subgraph-based framework for knowledge graph com- pletion with large language models. Information Fusion, 2024.","title":"Gs-kgc: A generative subgraph-based framework for knowledge graph completion with large language models","authors":"Rui Yang, Jiahao Zhu, Jianping Man, Hongze Liu, Li Fang, Yi Zhou","year":"2024","venue":"Information Fusion","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yao et al., 2021] Liang Yao, Chengsheng Mao, and Yuan Luo. KG-BERT: BERT for knowledge graph completion. CoRR, abs/1909.03193, 2021.","title":"KG-BERT: BERT for knowledge graph completion","authors":"Liang Yao, Chengsheng Mao, Yuan Luo","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zha et al., 2021] Hanwen Zha, Zhiyu Chen, and Xifeng Yan. Inductive relation prediction by bert. ArXiv, abs/2103.07102, 2021.","title":"Inductive relation prediction by bert","authors":"Zha","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhu et al., 2023] Yuqi Zhu, Xiaohan Wang, Jing Chen, Shuofei Qiao, Yixin Ou, Yunzhi Yao, Shumin Deng, Hua- jun Chen, and Ningyu Zhang. Llms for knowledge graph construction and reasoning: Recent capabilities and future opportunities. World Wide Web (WWW), 27:58, 2023.","title":"Llms for knowledge graph construction and reasoning: Recent capabilities and future opportunities","authors":"Yuqi Zhu, Xiaohan Wang, Jing Chen, Shuofei Qiao, Yixin Ou, Yunzhi Yao, Shumin Deng, Huajun Chen, Ningyu Zhang","year":"2023","venue":"World Wide Web (WWW)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}