PreGress: Ranking-Native Pre-training and Prompting for Graph Node Ranking

2026-08-09

AI Summary

Existing graph neural networks exhibit limited generalization in node ranking tasks, often requiring retraining for different ranking criteria and suffering from poor transfer performance due to misalignment between pretraining objectives and downstream ranking goals. To address these limitations, this work proposes the first native pretraining and prompting framework tailored specifically for node ranking. The approach introduces multitask pretraining objectives—such as degree centrality prediction and attribute reconstruction—that are inherently aligned with ranking tasks, coupled with lightweight, plug-and-play task-specific prompt modules. These prompts enable efficient adaptation to diverse ranking tasks while keeping the backbone network frozen. Extensive experiments on six public graph benchmarks, along with Yelp2018 and MovieLens-100K, demonstrate that the proposed method significantly improves cross-task ranking performance while substantially reducing task adaptation overhead.

Abstract

Node ranking is a fundamental problem in graph information retrieval, measuring the relative importance of nodes and supporting a wide range of applications such as influence analysis, recommendation, and graph-based retrieval augmented generation. However, exact computation of graph-based ranking measures is often computationally prohibitive at scale. Existing GNN-based ranking methods provide scalable approximations, but they are typically tailored to individual ranking criteria and require retraining for each downstream task, which limits their transferability and efficiency. Recent graph pre-training approaches aim to enable knowledge transfer across tasks, yet their learning objectives are largely misaligned with node ranking, resulting in suboptimal adaptability to ranking-oriented applications. To address these limitations, we propose PreGress, the first ranking-native pre-training and prompting framework for supporting a wide range of node ranking tasks. PreGress performs multi-task pre-training using our carefully designed objectives, including degree centrality prediction and attribute reconstruction, to jointly capture structural and attribute information. To support heterogeneous ranking criteria, we design lightweight, task-specific prompt modules that adapt a frozen ranking backbone to downstream tasks without full retraining. Experiments on six public graphs and two real-world query-to-item benchmarks---Yelp2018 and MovieLens-100K---together with a controlled five-criterion graph-access study demonstrate strong ranking quality with low task-specific state overhead.

Problem

• node ranking
• graph neural networks
• pre-training
• transferability
• ranking criteria

Innovation

• ranking-native pre-training
• graph node ranking
• prompting
• multi-task pre-training
• GNN