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

TL;DR

This paper introduces RawNP, a neural process-based model utilizing relational anonymous walks to improve few-shot inductive link prediction on knowledge graphs, achieving state-of-the-art results.

Contribution

It proposes a novel neural process approach with relational anonymous walks to better model inductive patterns in few-shot scenarios on KGs.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively models uncertainty in link prediction.

Captures semantic patterns with relational anonymous walks.

Abstract

Few-shot inductive link prediction on knowledge graphs (KGs) aims to predict missing links for unseen entities with few-shot links observed. Previous methods are limited to transductive scenarios, where entities exist in the knowledge graphs, so they are unable to handle unseen entities. Therefore, recent inductive methods utilize the sub-graphs around unseen entities to obtain the semantics and predict links inductively. However, in the few-shot setting, the sub-graphs are often sparse and cannot provide meaningful inductive patterns. In this paper, we propose a novel relational anonymous walk-guided neural process for few-shot inductive link prediction on knowledge graphs, denoted as RawNP. Specifically, we develop a neural process-based method to model a flexible distribution over link prediction functions. This enables the model to quickly adapt to new entities and estimate the uncertainty when making predictions. To capture general inductive patterns, we present a relational anonymous walk to extract a series of relational motifs from few-shot observations. These motifs reveal the distinctive semantic patterns on KGs that support inductive predictions. Extensive experiments on typical benchmark datasets demonstrate that our model derives new state-of-the-art performance.