Multi-relational graph contrastive learning with learnable graph augmentation

X Mo, J Pang, B Wan, R Tang, H Liu, S Jiang - Neural Networks, 2025 - Elsevier
Multi-relational graph learning aims to embed entities and relations in knowledge graphs
into low-dimensional representations, which has been successfully applied to various multi …

Clinical trial recommendations using Semantics-Based inductive inference and knowledge graph embeddings

MV Devarakonda, S Mohanty, RR Sunkishala… - Journal of biomedical …, 2024 - Elsevier
Objective Designing a new clinical trial entails many decisions, such as defining a cohort
and setting the study objectives to name a few, and therefore can benefit from …

GPL-GNN: Graph prompt learning for graph neural network

Z Chen, Y Wang, F Ma, H Yuan, X Wang - Knowledge-Based Systems, 2024 - Elsevier
Despite the impressive results achieved in many areas of graph machine learning, through
graph representation learning using supervised learning techniques, the limited availability …

Generalize to Fully Unseen Graphs: Learn Transferable Hyper-Relation Structures for Inductive Link Prediction

J Yang, X Jiang, Y Gao, LT Yang, J Yang - Proceedings of the 32nd ACM …, 2024 - dl.acm.org
Inductive link prediction aims to infer missing triples on unseen graphs, which contain
unseen entities and relations during training. The performances of existing inductive …

Beyond Transduction: A Survey on Inductive, Few Shot, and Zero Shot Link Prediction in Knowledge Graphs

N Hubert, P Monnin, H Paulheim - arXiv preprint arXiv:2312.04997, 2023 - arxiv.org
Knowledge graphs (KGs) comprise entities interconnected by relations of different semantic
meanings. KGs are being used in a wide range of applications. However, they inherently …

One Subgraph for All: Efficient Reasoning on Opening Subgraphs for Inductive Knowledge Graph Completion

Z Xie, Y Zhang, G Zhou, J Liu, X Tu… - arXiv preprint arXiv …, 2024 - arxiv.org
Knowledge Graph Completion (KGC) has garnered massive research interest recently, and
most existing methods are designed following a transductive setting where all entities are …