Few-shot knowledge graph completion refers to inferring missing entity using limited instances. A key challenge lies in entity representation, which is complicated by diverse neighbor attributes. Although the entity's neighborhood topology holds potential to address this, its significance is overlooked in current research. In this paper, we propose a structure-aware graph attention network for few-shot knowledge graph completion. Firstly, to enhance entity representations, we design a structure-aware graph attention encoder to capture the graph's structural features of nodes, generating embedding for entity pairs. Secondly, a semantic prototype matching network is employed to compute the prediction score. Experiments on the NELL-One and Wiki-One datasets show that our proposed model outperforms the best baseline models by 0.021, 0.026, 0.039, 0.032 and 0.016, 0.064, 0.043, 0.040 in terms of MRR, Hits@10, Hits@5, and Hits@1 metrics, respectively. This demonstrates that our model can effectively leverage neighborhood topological information to improve the accuracy of knowledge completion, and achieve a better generalization.
Yang Rongtai, Shao Yubin, Du Qingzhi, Zhang Feng, Qi Yuting
. Few-Shot Knowledge Graph Completion with Structure-Aware Graph Attention Network[J]. Journal of Shanghai Jiaotong University(Science), 2026
, 31(4)
: 1024
-1033
.
DOI: 10.1007/s12204-024-2781-5
[1] ZHANG T C, TIAN X, SUN X H, et al. Overview on knowledge graph embedding technology research [J]. Journal of Software, 2023, 34(1): 277-311 (in Chinese).
[2] ZHONG L F, WU J, LI Q, et al. A comprehensive survey on automatic knowledge graph construction [J]. ACM Computing Surveys, 2024, 56(4): 1-62.
[3] WEI Y B, HUANG Q S, ZHANG Y, et al. KICGPT: Large language model with knowledge in context for knowledge graph completion [C]// 2023 Conference on Empirical Methods in Natural Language Processing. Singapore: ACL, 2023: 8667-8683.
[4] ZHAO K L, JIN X L, WANG Y Z. Survey on few-shot learning [J]. Journal of Software, 2021, 32(2): 349-369 (in Chinese).
[5] LU J, GONG P H, YE J P, et al. A survey on machine learning from few samples [J]. Pattern Recognition, 2023, 139: 109480.
[6] HUANG Q, REN H Y, LESKOVEC J. Few-shot relational reasoning via connection subgraph pretraining [C]// 36th Conference on Neural Information Processing Systems. New Orleans: NIPS, 2022: 6397-6409.
[7] XIONG W H, YU M, CHANG S Y, et al. One-shot relational learning for knowledge graphs [C]// 2018 Conference on Empirical Methods in Natural Language Processing. Brussels: ACL, 2018: 1980–1990.
[8] ZHANG C X, YAO H X, HUANG C, et al. Few-shot knowledge graph completion [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(3): 3041-3048.
[9] SHENG J W, GUO S, CHEN Z Y, et al. Adaptive attentional network for few-shot knowledge graph completion [C]// 2020 Conference on Empirical Methods in Natural Language Processing. Online.: ACL, 2020: 1681-1691.
[10] CHEN M Y, ZHANG W, ZHANG W, et al. Meta relational learning for few-shot link prediction in knowledge graphs [C]// 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hong Kong: ACL, 2019: 4217-4226.
[11] ZHENG S J, MAI S J, SUN Y, et al. Subgraph-aware few-shot inductive link prediction via meta-learning [J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(6): 6512-6517.
[12] YAO S Y, ZHAO T Z, XU F Z, et al. Incorporating prior type information for few-shot knowledge graph completion [M]// Web and big data. Cham: Springer, 2023: 271-285.
[13] DWIVEDI V P, BRESSON X. A generalization of transformer networks to graphs [DB/OL]. (2020-12-17). https://arxiv.org/abs/2012.09699
[14] YING C X, CAI T L, LUO S J, et al. Do transformers really perform badly for graph representation?[C]// 35th Conference on Neural Information Processing Systems. Online: NIPS, 2021: 28877-28888.
[15] CHEN D X, O’BRAY L, BORGWARDT K. Structure-aware transformer for graph representation learning [C]// 39th International Conference on Machine Learning. Baltimore: PMLR, 2022: 3469-3489.
[16] LUO Y K, THOST V, SHI L. Transformers over directed acyclic graphs[C]// 37th Conference on Neural Information Processing Systems. New Orleans: NIPS, 2023: 47764-47782.
[17] VELIČKOVIĆ P, CASANOVA A, LIÒ P, et al. Graph attention networks [DB/OL]. (2017-10-30). https://arxiv.org/abs/1710.10903
[18] WANG X, HE X N, CAO Y X, et al. KGAT: Knowledge graph attention network for recommendation [C]// 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Anchorage: ACM, 2019: 950-958.
[19] YE Y, JI S H. Sparse graph attention networks [J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(1): 905-916.
[20] SU G X, WANG H C, ZHANG Y, et al. Simple and deep graph attention networks [J]. Knowledge-Based Systems, 2024, 293: 111649.
[21] DING L, LI C, JIN D, et al. Survey of spectral clustering based on graph theory [J]. Pattern Recognition, 2024, 151: 110366.
[22] YUAN H, JI S W. Structpool: structured graph pooling via conditional random fields [C]// International Conference on Learning Representations. Online: OpenReview Conference Foundation, 2020: 1-12
[23] BIANCHI F M, GRATTAROLA D, ALIPPI C. Spectral clustering with graph neural networks for graph pooling [DB/OL]. (2019-06-30). https://arxiv.org/abs/1907.00481
[24] BAEK J, KANG M, HWANG S J. Accurate learning of graph representations with graph multiset pooling [C]// International Conference on Learning Representations. Online: OpenReview Conference Foundation, 2021: 1-22.
[25] WU T, MA H Y, WANG C, et al. Heterogeneous representation learning and matching for few-shot relation prediction [J]. Pattern Recognition, 2022, 131: 108830.
[26] LIANG Y, ZHAO S, CHENG B, et al. TransAM: Transformer appending matcher for few-shot knowledge graph completion [J]. Neurocomputing, 2023, 537: 61-72.
[27] LI Y L, YU K, ZHANG Y H, et al. Adaptive prototype interaction network for few-shot knowledge graph completion [J]. IEEE Transactions on Neural Networks and Learning Systems, 2023. https://doi.org/10.1109/TNNLS.2023.3283545
[28] NIU G L, LI Y, TANG C G, et al. Relational learning with gated and attentive neighbor aggregator for few-shot knowledge graph completion [C]// 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. Online: ACM, 2021: 213-222.
[29] ZHANG Y M, QIAN Y Y, YE Y F, et al. Adapting distilled knowledge for few-shot relation reasoning over knowledge graphs [M]// 2022 SIAM International Conference on Data Mining. Philadelphia: Society for Industrial and Applied Mathematics, 2022: 666-674.
[30] CAI L Q, WANG L J, YUAN R D, et al. Meta-learning based dynamic adaptive relation learning for few-shot knowledge graph completion [J]. Big Data Research, 2023, 33: 100394.
