TY - GEN
T1 - Few-Shot Knowledge Graph Completion via Transfer Knowledge from Similar Tasks
AU - Liu, Lihui
AU - Wang, Zihao
AU - Zhou, Dawei
AU - Wang, Ruijie
AU - Yan, Yuchen
AU - Xiong, Bo
AU - He, Sihong
AU - Tong, Hanghang
N1 - Publisher Copyright:
© 2025 Copyright held by the owner/author(s).
PY - 2025/11/10
Y1 - 2025/11/10
N2 - Knowledge graphs (KGs) are essential in many AI applications but often suffer from incompleteness, limiting their utility. Many relations in KGs have only a few examples, making it challenging to train accurate models. Few-shot learning offers a promising direction by enabling KG completion with only a small number of training triplets. However, most existing approaches treat each relation independently and fail to leverage shared information across tasks. In this paper, we introduce TransNet, a transfer learning method for few-shot KG completion that captures task relationships and reuses knowledge from related tasks. TransNet further incorporates meta-learning to effectively handle unseen relations. Experiments on standard benchmarks demonstrate that TransNet achieves strong performance compared to prior methods. Code and data will be released upon acceptance.
AB - Knowledge graphs (KGs) are essential in many AI applications but often suffer from incompleteness, limiting their utility. Many relations in KGs have only a few examples, making it challenging to train accurate models. Few-shot learning offers a promising direction by enabling KG completion with only a small number of training triplets. However, most existing approaches treat each relation independently and fail to leverage shared information across tasks. In this paper, we introduce TransNet, a transfer learning method for few-shot KG completion that captures task relationships and reuses knowledge from related tasks. TransNet further incorporates meta-learning to effectively handle unseen relations. Experiments on standard benchmarks demonstrate that TransNet achieves strong performance compared to prior methods. Code and data will be released upon acceptance.
KW - few shot learning
KW - knowledge graph completion
KW - knowledge graph reasoning
KW - transfer learning
UR - https://www.scopus.com/pages/publications/105023152418
U2 - 10.1145/3746252.3760843
DO - 10.1145/3746252.3760843
M3 - 会议稿件
AN - SCOPUS:105023152418
T3 - CIKM 2025 - Proceedings of the 34th ACM International Conference on Information and Knowledge Management
SP - 4960
EP - 4965
BT - CIKM 2025 - Proceedings of the 34th ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery, Inc
T2 - 34th ACM International Conference on Information and Knowledge Management, CIKM 2025
Y2 - 10 November 2025 through 14 November 2025
ER -