mlsanityData to 7 Oct 2026

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

arXiv 2608.09016 ↗First posted 10 Aug 2026cs.IR cs.LGcited by 0

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 29 of its 70 references that are in the map. First posted on arXiv 10 Aug 2026.

Builds on

29 of 70 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG13 Feb

Other references · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2017Graph Attention Networkscited by 8,854
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2017Inductive Representation Learning on Large Graphscited by 6,284
  8. 2018How Powerful are Graph Neural Networks?cited by 4,355
  9. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  10. 2019Neural Graph Collaborative Filteringcited by 660
  11. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  12. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 302
16 more
  1. 2020Can Graph Neural Networks Count Substructures?cited by 235
  2. 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 197
  3. 2022SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentationcited by 171
  4. 2021Nested Graph Neural Networkscited by 136
  5. 2019An Exponential Learning Rate Schedule for Deep Learningcited by 121
  6. 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 114
  7. 2020Subgraph Neural Networkscited by 73
  8. 2019SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrievalcited by 48
  9. 2023Generalized Graph Prompt: Toward a Unification of Pre-Training and Downstream Tasks on Graphscited by 39
  10. 2019Optimizing Generalized PageRank Methods for Seed-Expansion Community Detectioncited by 35
  11. 2023AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNscited by 26
  12. 2019On Application of Learning to Rank for E-Commerce Searchcited by 24
  13. 2019A Survey of Community Search Over Big Graphscited by 21
  14. 2017BiRank: Towards Ranking on Bipartite Graphscited by 15
  15. 2018Fast Matrix Factorization with Non-Uniform Weights on Missing Datacited by 12
  16. 2023Learning To Rank Resources with GNNcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024RAGraph: A General Retrieval-Augmented Graph Learning Framework
  2. 2025A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation
  3. 2025Graph-Based Re-ranking in Information Retrieval and Beyond: A Survey
  4. 2025Beyond Single-Granularity Prompts: A Multi-Scale Chain-of-Thought Prompt Learning for Graph
  5. 2026HopRank: Self-Supervised LLM Preference-Tuning on Graphs for Few-Shot Node Classification
  6. 2025Microsoft Academic Graph Information Retrieval for Research Recommendation and Assistance
  7. 2026Generalized Rank-based Evaluation for Knowledge Graph Completion: Perspectives, Framework, and Analyses
  8. 2025GMoPE:A Prompt-Expert Mixture Framework for Graph Foundation Models