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

2026-04-11

AI Summary

To address the scalability bottleneck in large-scale knowledge graph link prediction caused by global graph dependency, this paper proposes a “query-driven one-shot subgraph inference” paradigm. It efficiently extracts a single, highly relevant subgraph for each query via Personalized PageRank (PPR) and deploys a lightweight prediction model exclusively on that subgraph. This decouples inference from global graph structure, enabling adaptive, low-overhead reasoning. We further introduce the first joint automated search over both data space (subgraph topology) and model space (hyperparameters). Extensive experiments on five large-scale benchmarks demonstrate state-of-the-art performance: inference speed improves by 1.5–5.2×, and memory consumption reduces by 68%–93%. The code is publicly available.

Technology Category

Search and Optimization: Learning to SearchMachine Learning: Graph-based Machine LearningData Mining & Knowledge Management: Intelligent Query Processing

Application Category

Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Scalability issue in large-scale knowledge graphs
• Efficient subgraph extraction for link prediction
• Automated optimization of data and model configurations

Innovation

• One-shot subgraph link prediction
• Personalized PageRank heuristic
• Automated optimal configuration search