English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Few-shot inductive link prediction on knowledge graphs (KGs) aims to predictmissing links for unseen entities with few-shot links observed. Previousmethods are limited to transductive scenarios, where entities exist in theknowledge graphs, so they are unable to handle unseen entities. Therefore,recent inductive methods utilize the sub-graphs around unseen entities toobtain the semantics and predict links inductively. However, in the few-shotsetting, the sub-graphs are often sparse and cannot provide meaningfulinductive patterns. In this paper, we propose a novel relational anonymouswalk-guided neural process for few-shot inductive link prediction on knowledgegraphs, denoted as RawNP. Specifically, we develop a neural process-basedmethod to model a flexible distribution over link prediction functions. Thisenables the model to quickly adapt to new entities and estimate the uncertaintywhen making predictions. To capture general inductive patterns, we present arelational anonymous walk to extract a series of relational motifs fromfew-shot observations. These motifs reveal the distinctive semantic patterns onKGs that support inductive predictions. Extensive experiments on typicalbenchmark datasets demonstrate that our model derives new state-of-the-artperformance.

Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach