Timezone: »
The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i.e., embeddings) of entities and relations. However, these embedding-based methods do not explicitly capture the compositional logical rules underlying the knowledge graph, and they are limited to the transductive setting, where the full set of entities must be known during training. Here, we propose a graph neural network based relation prediction framework, GraIL, that reasons over local subgraph structures and has a strong inductive bias to learn entity-independent relational semantics. Unlike embedding-based models, GraIL is naturally inductive and can generalize to unseen entities and graphs after training. We provide theoretical proof and strong empirical evidence that GraIL can rep-resent a useful subset of first-order logic and show that GraIL outperforms existing rule-induction baselines in the inductive setting. We also demonstrate significant gains obtained by ensembling GraIL with various knowledge graph embedding methods in the transductive setting, highlighting the complementary inductive bias of our method.
Author Information
Komal Teru (Mila, McGill University)
Etienne Denis (McGill)
Will Hamilton (McGill University and Mila)
More from the Same Authors
-
2021 Poster: Directional Graph Networks »
Dominique Beaini · Saro Passaro · Vincent Létourneau · Will Hamilton · Gabriele Corso · Pietro Lió -
2021 Oral: Directional Graph Networks »
Dominique Beaini · Saro Passaro · Vincent Létourneau · Will Hamilton · Gabriele Corso · Pietro Lió -
2020 Workshop: Graph Representation Learning and Beyond (GRL+) »
Petar Veličković · Michael M. Bronstein · Andreea Deac · Will Hamilton · Jessica Hamrick · Milad Hashemi · Stefanie Jegelka · Jure Leskovec · Renjie Liao · Federico Monti · Yizhou Sun · Kevin Swersky · Rex (Zhitao) Ying · Marinka Zitnik -
2020 Poster: Latent Variable Modelling with Hyperbolic Normalizing Flows »
Joey Bose · Ariella Smofsky · Renjie Liao · Prakash Panangaden · Will Hamilton -
2019 : William L. Hamilton, McGill University »
Will Hamilton