Progressive Knowledge Graph Completion (2404.09897v1)
Abstract: Knowledge Graph Completion (KGC) has emerged as a promising solution to address the issue of incompleteness within Knowledge Graphs (KGs). Traditional KGC research primarily centers on triple classification and link prediction. Nevertheless, we contend that these tasks do not align well with real-world scenarios and merely serve as surrogate benchmarks. In this paper, we investigate three crucial processes relevant to real-world construction scenarios: (a) the verification process, which arises from the necessity and limitations of human verifiers; (b) the mining process, which identifies the most promising candidates for verification; and (c) the training process, which harnesses verified data for subsequent utilization; in order to achieve a transition toward more realistic challenges. By integrating these three processes, we introduce the Progressive Knowledge Graph Completion (PKGC) task, which simulates the gradual completion of KGs in real-world scenarios. Furthermore, to expedite PKGC processing, we propose two acceleration modules: Optimized Top-$k$ algorithm and Semantic Validity Filter. These modules significantly enhance the efficiency of the mining procedure. Our experiments demonstrate that performance in link prediction does not accurately reflect performance in PKGC. A more in-depth analysis reveals the key factors influencing the results and provides potential directions for future research.
- Accurate text-enhanced knowledge graph representation learning. In NAACL-HLT, pages 745–755.
- Multi-relational poincaré graph embeddings. In NeurIPS, pages 4465–4475.
- Translating embeddings for modeling multi-relational data. In NeurIPS, pages 2787–2795.
- Low-dimensional hyperbolic knowledge graph embeddings. In ACL, pages 6901–6914.
- Hitter: Hierarchical transformers for knowledge graph embeddings. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021, pages 10395–10407. Association for Computational Linguistics.
- Introduction to algorithms. MIT press.
- Convolutional 2d knowledge graph embeddings. In AAAI, pages 1811–1818.
- Predicting completeness in knowledge bases. In WSDM, pages 375–383, Cambridge, UK.
- AMIE: association rule mining under incomplete evidence in ontological knowledge bases. In WWW, pages 413–422.
- Neural knowledge acquisition via mutual attention between knowledge graph and text. In AAAI, pages 4832–4839.
- Frank L Hitchcock. 1927. The expression of a tensor or a polyadic as a sum of products. Journal of Mathematics and Physics, 6(1-4):164–189.
- Open graph benchmark: Datasets for machine learning on graphs. In NeurIPS.
- A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Trans Neural Netw Learn Syst., pages 1–21.
- Prior bilinear based models for knowledge graph completion. CoRR, abs/2309.13834.
- Jiayi Li and Yujiu Yang. 2022. Star: Knowledge graph embedding by scaling, translation and rotation. arXiv preprint arXiv:2202.07130.
- Multi-hop knowledge graph reasoning with reward shaping. In EMNLP, pages 3243–3253.
- Learning entity and relation embeddings for knowledge graph completion. In AAAI, pages 2181–2187.
- RAGAT: relation aware graph attention network for knowledge graph completion. IEEE Access, 9:20840–20849.
- Strong baselines for simple question answering over knowledge graphs with and without neural networks. In NAACL-HLT (2), pages 291–296.
- A novel embedding model for knowledge base completion based on convolutional neural network. In NAACL-HLT (2), pages 327–333.
- A three-way model for collective learning on multi-relational data. In ICML, pages 809–816.
- An embedding-based approach to rule learning in knowledge graphs. IEEE Trans. Knowl. Data Eng., 33(4):1348–1359.
- Large language models and knowledge graphs: Opportunities and challenges. CoRR, abs/2308.06374.
- A survey of deep active learning. ACM Comput. Surv., 54(9):180:1–180:40.
- Modeling relational data with graph convolutional networks. In ESWC, volume 10843, pages 593–607.
- Rotate: Knowledge graph embedding by relational rotation in complex space. In ICLR.
- A re-evaluation of knowledge graph completion methods. arXiv preprint arXiv:1911.03903.
- KRACL: contrastive learning with graph context modeling for sparse knowledge graph completion. In Proceedings of the ACM Web Conference 2023, WWW 2023, Austin, TX, USA, 30 April 2023 - 4 May 2023, pages 2548–2559. ACM.
- Kristina Toutanova and Danqi Chen. 2015. Observed versus latent features for knowledge base and text inference. In Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality, pages 57–66, Beijing, China.
- Complex embeddings for simple link prediction. In ICML, volume 48, pages 2071–2080.
- Attention is all you need. In NeurIPS, pages 5998–6008.
- Knowledge graph embedding via graph attenuated attention networks. IEEE Access, 8:5212–5224.
- KEPLER: A unified model for knowledge embedding and pre-trained language representation. Trans. Assoc. Comput. Linguistics, 9:176–194.
- Knowledge graph and text jointly embedding. In EMNLP, pages 1591–1601.
- Knowledge graph embedding by translating on hyperplanes. In AAAI, pages 1112–1119.
- Representation learning of knowledge graphs with entity descriptions. In AAAI, pages 2659–2665.
- Deeppath: A reinforcement learning method for knowledge graph reasoning. In EMNLP, pages 564–573.
- KG-BERT: BERT for knowledge graph completion. CoRR, abs/1909.03193.
- Collaborative knowledge base embedding for recommender systems. In KDD, pages 353–362.
- Quaternion knowledge graph embeddings. In NeurIPS, pages 2731–2741.
- Trans: Transition-based knowledge graph embedding with synthetic relation representation. In Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022, pages 1202–1208. Association for Computational Linguistics.