mlsanityData to 14 Oct 2026

Adaptive Recurrent Message Passing for Test Time Computing on Graphs

arXiv 2606.22462 ↗First posted 21 Jun 2026cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Pre-trained foundation models have demonstrated remarkable success in many domains, enabling a unified backbone to generalize across diverse downstream tasks. However, extending this paradigm to graph learning remains challenging due to the intrinsic mismatch between graph data and fixed architectural designs. In this work, we show that this limitation can be overcome via recurrent graph models. To achieve this, we conduct a systematic theoretical analysis, rigorously deriving step dependence as a necessary and sufficient condition for an adaptively convergent recurrent process. Building on this foundation, we propose AdaR, an Adaptive Recurrent graph model, empowering flexible test-time computing on various downstream tasks without changing model parameters. To enable adaptive inference, AdaR explicitly encodes normalized step information and representation-target relations into the recurrent updates. To ensure convergence of the recurrent process, AdaR employs gradient-based supervision signals that guide representation updates throughout the recurrence. Empirical results demonstrate that AdaR consistently outperforms strong baselines in both inductive and transductive settings.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 54 of its 64 references that are in the map. First posted on arXiv 21 Jun 2026.

Builds on

54 of 64 references.

References · 54

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2018Deep Graph Infomaxcited by 1,106
  7. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  8. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  9. 2020Simple and Deep Graph Convolutional Networkscited by 860
  10. 2015Gated Graph Sequence Neural Networkscited by 796
  11. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
  12. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
38 more
  1. 2020Deep Graph Contrastive Representation Learningcited by 539
  2. 2021Rethinking Graph Transformers with Spectral Attentioncited by 473
  3. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 463
  4. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 362
  5. 2017Residual Gated Graph ConvNetscited by 346
  6. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  7. 2021Do Transformers Really Perform Bad for Graph Representation?cited by 320
  8. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 303
  9. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 243
  10. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 226
  11. 2018Learning a SAT Solver from Single-Bit Supervisioncited by 200
  12. 2024LLaGA: Large Language and Graph Assistantcited by 181
  13. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  14. 2023Exphormer: Sparse Transformers for Graphscited by 170
  15. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 167
  16. 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 148
  17. 2022NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphscited by 137
  18. 2022Universal Prompt Tuning for Graph Neural Networkscited by 100
  19. 2023PRODIGY: Enabling In-context Learning Over Graphscited by 98
  20. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 86
  21. 2024ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphscited by 85
  22. 2024GFT: Graph Foundation Model with Transferable Tree Vocabularycited by 85
  23. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 78
  24. 2024Can GNN be Good Adapter for LLMs?cited by 71
  25. 2023Graph Neural Prompting with Large Language Modelscited by 64
  26. 2024GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Taskscited by 63
  27. 2020Gated Graph Recurrent Neural Networkscited by 58
  28. 2024GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphscited by 58
  29. 2024GOFA: A Generative One-For-All Model for Joint Graph Language Modelingcited by 57
  30. 2022Message passing all the way upcited by 47
  31. 2023Virtual Node Tuning for Few-shot Node Classificationcited by 46
  32. 2024Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insightscited by 44
  33. 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignmentcited by 42
  34. 2023MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphscited by 40
  35. 2023AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNscited by 26
  36. 2023G-Adapter: Towards Structure-Aware Parameter-Efficient Transfer Learning for Graph Transformer Networkscited by 25
  37. 2024Let's Ask GNN: Empowering Large Language Model for Graph In-Context Learningcited by 21
  38. 2024Distilling Large Language Models for Text-Attributed Graph Learningcited by 20

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Tiny Recursive Message Passingcited by 0