Abstract
The relation learning between two entities is an essential task in knowledge graph (KG) completion that has received much attention recently. Previous work almost exclusively focused on relations widely seen in the original KGs, which means that enough training data are available for modeling. However, long-tail relations that only show in a few triples are actually much more common in practical KGs. Without sufficiently large training data, the performance of existing models on predicting long-tail relations drops impressively. This work aims to predict the relation under a challenging setting where only one instance is available for training. We propose a path-based one-shot relation prediction framework, which can extract neighborhood information of an entity based on the relation query attention mechanism to learn transferable knowledge among the same relation. Simultaneously, to reduce the impact of long-tail entities on relation prediction, we selectively fuse path information between entity pairs as auxiliary information of relation features. Experiments in three one-shot relation learning datasets show that our proposed framework substantially outperforms existing models on one-shot link prediction and relation prediction.
- [1] . 2007. DBpedia: A nucleus for a web of open data. In The Semantic Web. Springer, Berlin, Germany, 722–735. Google Scholar
Digital Library
- [2] . 2019. TuckER: Tensor factorization for knowledge graph completion. arXiv preprint arXiv:1901.09590 (2019).Google Scholar
- [3] . 2013. Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems 26. Curran Associates, 2787–2795. http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf. Google Scholar
Digital Library
- [4] . 2019. Meta relational learning for few-shot link prediction in knowledge graphs. arXiv preprint arXiv:1909.01515 (2019).Google Scholar
- [5] . 2017. Chains of reasoning over entities, relations, and text using recurrent neural networks. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers. 132–141. https://www.aclweb.org/anthology/E17-1013.Google Scholar
Cross Ref
- [6] . 2019. Cognitive knowledge graph reasoning for one-shot relational learning. CoRR abs/1906.05489 (2019). arXiv:1906.05489 http://arxiv.org/abs/1906.05489.Google Scholar
- [7] . 2017. Model-agnostic meta-learning for fast adaptation of deep networks. CoRR abs/1703.03400 (2017). arXiv:1703.03400 http://arxiv.org/abs/1703.03400. Google Scholar
Digital Library
- [8] . 2019. Hybrid attention-based prototypical networks for noisy few-shot relation classification. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI’19). Google Scholar
Digital Library
- [9] . 2019. Neural snowball for few-shot relation learning. ArXiv abs/1908.11007 (2019).Google Scholar
- [10] . 2018. FewRel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 4803–4809.
DOI: DOI: https://doi.org/10.18653/v1/D18-1514Google ScholarCross Ref
- [11] . 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- [12] . 2015. Siamese neural networks for one-shot image recognition. In ICML Deep Learning Workshop, vol. 2.Google Scholar
- [13] . 2010. Relational retrieval using a combination of path-constrained random walks. Machine Learning 81, 1 (2010), 53–67. Google Scholar
Digital Library
- [14] . 2020. Few-shot named entity recognition via meta-learning. IEEE Transactions on Knowledge and Data Engineering. Early access, November 17, 2020.
DOI: DOI: https://doi.org/10.1109/TKDE.2020.3038670Google ScholarCross Ref
- [15] . 2017. Meta-SGD: Learning to learn quickly for few shot learning. CoRR abs/1707.09835 (2017). arXiv:1707.09835 http://arxiv.org/abs/1707.09835.Google Scholar
- [16] . 2019. Adapting meta knowledge graph information for multi-hop reasoning over few-shot relations. arXiv preprint arXiv:1908.11513 (2019).Google Scholar
- [17] . 2015. YAGO3: A knowledge base from multilingual Wikipedias. In Proceedings of the 7th Biennial Conference on Innovative Data Systems Research (CIDR’15).Google Scholar
- [18] . 2018. Never-ending learning. Communications of the ACM 61, 5 (
April 2018), 103–115.DOI: DOI: https://doi.org/10.1145/3191513 Google ScholarCross Ref
- [19] . 2015. Compositional vector space models for knowledge base completion. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 156–166.
DOI: DOI: https://doi.org/10.3115/v1/P15-1016Google ScholarCross Ref
- [20] . 2011. A three-way model for collective learning on multi-relational data. In Proceedings of the 28th International Conference on Machine Learning (ICML’11). 809–816. Google Scholar
Digital Library
- [21] . 2020. Few-shot relation extraction via Bayesian meta-learning on relation graphs. In Proceedings of the International Conference on Machine Learning. 7867–7876.Google Scholar
- [22] . 2017. Optimization as a model for few-shot learning. In Proceedings of the International Conference on Learning Representations.Google Scholar
- [23] . 2016. One-shot learning with memory-augmented neural networks. arXiv preprint arXiv:1605.06065 (2016).Google Scholar
- [24] . 2020. Adaptive attentional network for few-shot knowledge graph completion. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP’20). 1681–1691.
DOI: DOI: https://doi.org/10.18653/v1/2020.emnlp-main.131Google ScholarCross Ref
- [25] . 2017. Prototypical networks for few-shot learning. In Advances in Neural Information Processing Systems. 4077–4087. Google Scholar
Digital Library
- [26] . 2019. RotatE: Knowledge graph embedding by relational rotation in complex space. In Proceedings of the International Conference on Learning Representations. https://openreview.net/forum?id=HkgEQnRqYQ.Google Scholar
- [27] . 2019. RotatE: Knowledge graph embedding by relational rotation in complex space. arXiv:1902.10197 (2019).Google Scholar
- [28] . 2018. Learning to compare: Relation network for few-shot learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1199–1208.Google Scholar
Cross Ref
- [29] . 2016. Complex embeddings for simple link prediction. In Proceedings of the International Conference on Machine Learning. 2071–2080. Google Scholar
Digital Library
- [30] . 2016. Matching networks for one shot learning. In Advances in Neural Information Processing Systems 29. https://proceedings.neurips.cc/paper/2016/file/90e1357833654983612fb05e3ec9148c-Paper.pdf. Google Scholar
Digital Library
- [31] . 2014. Wikidata: A free collaborative knowledge base. Communications of the ACM 57 (2014), 78–85. http://cacm.acm.org/magazines/2014/10/178785-wikidata/fulltext. Google Scholar
Digital Library
- [32] . 2020. Entity context and relational paths for knowledge graph completion. arXiv preprint arXiv:2002.06757 (2020).Google Scholar
- [33] . 2019. Are you for real? Detecting identity fraud via dialogue interactions. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP’19). 1762–1771.
DOI: DOI: https://doi.org/10.18653/v1/D19-1185Google ScholarCross Ref
- [34] . 2014. Knowledge graph embedding by translating on hyperplanes. In Proceedings of the 28th AAAI Conference on Artificial Intelligence. Google Scholar
Digital Library
- [35] . 2018. One-shot relational learning for knowledge graphs. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.1980–1990. https://aclanthology.info/papers/D18-1223/d18-1223.Google Scholar
Cross Ref
- [36] . 2020. A knowledge-driven generative model for multi-implication Chinese medical procedure entity normalization. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.Google Scholar
Cross Ref
- [37] . 2014. Embedding entities and relations for learning and inference in knowledge bases. In Proceedings of the International Conference on Learning Representations.Google Scholar
- [38] . 2019. Multi-level matching and aggregation network for few-shot relation classification. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2872–2881.Google Scholar
Cross Ref
- [39] . 2018. Diverse few-shot text classification with multiple metrics. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 1206–1215.
DOI: DOI: https://doi.org/10.18653/v1/N18-1109Google ScholarCross Ref
- [40] . 2020. Few-shot knowledge graph completion. Proceedings of the AAAI Conference on Artificial Intelligence 34, 3 (
April 2020), 3041–3048.DOI: DOI: https://doi.org/10.1609/aaai.v34i03.5698Google ScholarCross Ref
- [41] . 2019. Long-tail relation extraction via knowledge graph embeddings and graph convolution networks. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 3016–3025.
DOI: DOI: https://doi.org/10.18653/v1/N19-1306Google ScholarCross Ref
- [42] . 2020. Knowledge graphs enhanced neural machine translation. In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI’20). 4039–4045. Google Scholar
Digital Library
- [43] . 2021. Text Data Mining. Springer.Google Scholar
Cross Ref
Index Terms
One-Shot Relation Learning for Knowledge Graphs via Neighborhood Aggregation and Paths Encoding
Recommendations
Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information RetrievalAiming at expanding few-shot relations' coverage in knowledge graphs (KGs), few-shot knowledge graph completion (FKGC) has recently gained more research interests. Some existing models employ a few-shot relation's multi-hop neighbor information to ...
MetaP: Meta Pattern Learning for One-Shot Knowledge Graph Completion
SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information RetrievalKnowledge Graphs (KGs) are widely used in various applications of information retrieval. Despite the large scale of KGs, they are still facing incomplete problems. Conventional approaches on Knowledge Graph Completion (KGC) require a large number of ...
Zero-Shot Knowledge Graph Completion for Recommendation System
Intelligent Data Engineering and Automated Learning – IDEAL 2022AbstractKnowledge graphs are structured representations of actual entities and relations. They are widely used to improve the performance of downstream tasks such as recommendation systems and semantic searching. Knowledge graph completion (KGC) is a ...






Comments