2000 character limit reached
Meta Operator for Complex Query Answering on Knowledge Graphs (2403.10110v1)
Published 15 Mar 2024 in cs.LG, cs.AI, and cs.LO
Abstract: Knowledge graphs contain informative factual knowledge but are considered incomplete. To answer complex queries under incomplete knowledge, learning-based Complex Query Answering (CQA) models are proposed to directly learn from the query-answer samples to avoid the direct traversal of incomplete graph data. Existing works formulate the training of complex query answering models as multi-task learning and require a large number of training samples. In this work, we explore the compositional structure of complex queries and argue that the different logical operator types, rather than the different complex query types, are the key to improving generalizability. Accordingly, we propose a meta-learning algorithm to learn the meta-operators with limited data and adapt them to different instances of operators under various complex queries. Empirical results show that learning meta-operators is more effective than learning original CQA or meta-CQA models.
- Neural Methods for Logical Reasoning over Knowledge Graphs. October 2021. URL https://openreview.net/forum?id=tgcAoUVHRIB.
- Complex Query Answering with Neural Link Predictors. In International Conference on Learning Representations, 2020.
- Query2Particles: Knowledge Graph Reasoning with Particle Embeddings. In Findings of the Association for Computational Linguistics: NAACL 2022, pp. 2703–2714, 2022.
- Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints, May 2023a. URL http://arxiv.org/abs/2305.19068. arXiv:2305.19068 [cs].
- Knowledge Graph Reasoning over Entities and Numerical Values. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’23, pp. 57–68, New York, NY, USA, August 2023b. Association for Computing Machinery. ISBN 9798400701030. doi: 10.1145/3580305.3599399. URL https://dl.acm.org/doi/10.1145/3580305.3599399.
- Unobserved local structures make compositional generalization hard. arXiv preprint arXiv:2201.05899, 2022.
- Toward an architecture for never-ending language learning. In Proceedings of the AAAI conference on artificial intelligence, volume 24, pp. 1306–1313, 2010. Issue: 1.
- Fuzzy logic based logical query answering on knowledge graphs. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pp. 3939–3948, 2022. Issue: 4.
- Probabilistic entity representation model for reasoning over knowledge graphs. Advances in Neural Information Processing Systems, 34:23440–23451, 2021.
- Soft Reasoning on Uncertain Knowledge Graphs, March 2024. URL http://arxiv.org/abs/2403.01508. arXiv:2403.01508 [cs].
- Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning, pp. 1126–1135. PMLR, 2017.
- Meta-Learning in Neural Networks: A Survey, November 2020. URL http://arxiv.org/abs/2004.05439. arXiv:2004.05439 [cs, stat].
- Open and Closed World Assumptions in Data Exchange. Description Logics, 477, 2009.
- Neural-Answering Logical Queries on Knowledge Graphs. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1087–1097, 2021.
- Logic embeddings for complex query answering. arXiv preprint arXiv:2103.00418, 2021.
- Rapid learning or feature reuse? towards understanding the effectiveness of maml. arXiv preprint arXiv:1909.09157, 2019.
- Query2box: Reasoning Over Knowledge Graphs In Vector Space Using Box Embeddings. In International Conference on Learning Representations (ICLR), 2020.
- Beta embeddings for multi-hop logical reasoning in knowledge graphs. Advances in Neural Information Processing Systems, 33:19716–19726, 2020.
- Lego: Latent execution-guided reasoning for multi-hop question answering on knowledge graphs. In International Conference on Machine Learning, pp. 8959–8970. PMLR, 2021.
- Fact Ranking over Large-Scale Knowledge Graphs with Reasoning Embedding Models. Data Engineering, pp. 124, 2023.
- Observed versus latent features for knowledge base and text inference. In Proceedings of the 3rd workshop on continuous vector space models and their compositionality, pp. 57–66, 2015.
- Matching networks for one shot learning. Advances in neural information processing systems, 29, 2016.
- Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs. Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, 1, December 2021. URL https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/7eabe3a1649ffa2b3ff8c02ebfd5659f-Abstract-round2.html.
- Logical Queries on Knowledge Graphs: Emerging Interface of Incomplete Relational Data. Data Engineering, pp. 3, 2022.
- Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport. arXiv preprint arXiv:2305.04034, 2023a.
- Logical Message Passing Networks with One-hop Inference on Atomic Formulas. In The Eleventh International Conference on Learning Representations, 2023b. URL https://openreview.net/forum?id=SoyOsp7i_l.
- $\text{EFO}_{k}$-CQA: Towards Knowledge Graph Complex Query Answering beyond Set Operation, July 2023a. URL http://arxiv.org/abs/2307.13701. arXiv:2307.13701 [cs].
- On Existential First Order Queries Inference on Knowledge Graphs, April 2023b. URL http://arxiv.org/abs/2304.07063. arXiv:2304.07063 [cs].
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors. October 2023c. URL https://openreview.net/forum?id=1BmveEMNbG.
- Cone: Cone embeddings for multi-hop reasoning over knowledge graphs. Advances in Neural Information Processing Systems, 34:19172–19183, 2021.
- Meta-gnn: On few-shot node classification in graph meta-learning. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 2357–2360, 2019.