Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs

TL;DR

This paper introduces a scalable one-shot subgraph reasoning method for large-scale knowledge graphs, which extracts a single relevant subgraph per query and predicts efficiently, outperforming existing approaches.

Contribution

It proposes a novel two-step prediction approach that decouples subgraph extraction from prediction, utilizing Personalized PageRank for efficient answer identification.

Findings

Achieves higher efficiency on large-scale KGs.

Outperforms existing methods on five benchmarks.

Enables automated configuration search for optimal performance.

Abstract

To deduce new facts on a knowledge graph (KG), a link predictor learns from the graph structure and collects local evidence to find the answer to a given query. However, existing methods suffer from a severe scalability problem due to the utilization of the whole KG for prediction, which hinders their promise on large scale KGs and cannot be directly addressed by vanilla sampling methods. In this work, we propose the one-shot-subgraph link prediction to achieve efficient and adaptive prediction. The design principle is that, instead of directly acting on the whole KG, the prediction procedure is decoupled into two steps, i.e., (i) extracting only one subgraph according to the query and (ii) predicting on this single, query dependent subgraph. We reveal that the non-parametric and computation-efficient heuristics Personalized PageRank (PPR) can effectively identify the potential answers and supporting evidence. With efficient subgraph-based prediction, we further introduce the automated searching of the optimal configurations in both data and model spaces. Empirically, we achieve promoted efficiency and leading performances on five large-scale benchmarks. The code is publicly available at: https://github.com/tmlr-group/one-shot-subgraph.