This paper proposes HD-SKRG, a hierarchical dual-view and structure-knowledge relation graph enhancement network that improves few-shot prediction from two complementary aspects: molecular representation learning and intra-task relation propagation.
Few-shot knowledge graph completion aims to predict missing triplets involving few-shot relations, where each few-shot relation is associated with only a few examples of the relation, called support triplets. In few-shot knowledge graph completion, each few-shot task corresponds to predicting triplets for a few-shot re...
Chanyoung Chung, Minsung Hwang, Joyce Jiyoung Whang· Proceedings of the 35th ACM...· 0 citations
Adaptive Relation-specific Weighted Ensemble (AReWE) is proposed, a relation-aware ensemble framework that jointly fine-tunes pretrained KGE models and achieves state-of-the-art performance on FB15K237 and NELL-995.
Huda Hakami, Danushka Bollegala· Transactions of the Associat...· 0 citations
An emerging approach called cross-domain recommendation transfers knowledge across heterogeneous areas, including books and movies, to improve the user experience. Existing methods often suffer from sparse interactions, semantic gaps across domains, and insufficient explainability. To address these limitations, we prop...
Sharmila Rani Jetti, M. H. M. Krishna Prasad· International Journal of Com...· 0 citations
Knowledge graph completion (KGC) aims to predict missing relationships between pairs of entities. Recently, Message Passing Neural Networks (MPNNs) have been employed in KGC and demonstrated superior ability in embedding learning. Current methods, however, face two major dilemmas. One focuses on learning complex entity...
Kang-Ye Wang, Peng-Wen Dai, Chuan Wang et al.· IEEE Transactions on Knowled...· 0 citations
Molecular property prediction is important for drug discovery, but labeled molecules are often limited for new prediction tasks. The difficulty is amplified in cross-domain few-shot settings, where target tasks differ from available source tasks and the model must adapt from sparse target-domain supervision. Existing f...
Tian-Yi Jiang, Shan-Qing Yu, Qi Xuan· Proceedings of the 35th ACM...· 0 citations
Heterogeneous information networks (HINs) contain rich type-aware semantics and complex relational structures, making effective representation learning challenging. Existing heterogeneous graph contrastive methods have explored cross-view alignment, but many construct semantic views through holistic meta-path or neighb...
Jin-Long Ma, Pei-Lin Cheng· Engineering Research Express· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.