Inductive Relation Prediction
9 papers with code • 0 benchmarks • 0 datasets
Inductive setting of the knowledge graph completion task. This requires a model to perform link prediction on an entirely new test graph with new set of entities.
These leaderboards are used to track progress in Inductive Relation Prediction
The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i. e., embeddings) of entities and relations.
To further improve the capacity of the path formulation, we propose the Neural Bellman-Ford Network (NBFNet), a general graph neural network framework that solves the path formulation with learned operators in the generalized Bellman-Ford algorithm.
In this paper, we consider rules as cycles and show that the space of cycles has a unique structure based on the mathematics of algebraic topology.
In this paper, to achieve inductive knowledge graph embedding, we propose a model MorsE, which does not learn embeddings for entities but learns transferable meta-knowledge that can be used to produce entity embeddings.
Recent studies on knowledge graphs (KGs) show that path-based methods empowered by pre-trained language models perform well in the provision of inductive and explainable relation predictions.
In this work, we bridge the gap between traditional transductive knowledge graph embedding approaches and more recent inductive relation prediction models by introducing a generalized form of harmonic extension which leverages representations learned through transductive embedding methods to infer representations of new entities introduced at inference time as in the inductive setting.