mlsanityData to 14 Oct 2026

GraphBridge: Towards Arbitrary Transfer Learning in GNNs

arXiv 2502.19252 ↗First posted 26 Feb 2025cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) are conventionally trained on a per-domain, per-task basis. It creates a significant barrier in transferring the acquired knowledge to different, heterogeneous data setups. This paper introduces GraphBridge, a novel framework to enable knowledge transfer across disparate tasks and domains in GNNs, circumventing the need for modifications to task configurations or graph structures. Specifically, GraphBridge allows for the augmentation of any pre-trained GNN with prediction heads and a bridging network that connects the input to the output layer. This architecture not only preserves the intrinsic knowledge of the original model but also supports outputs of arbitrary dimensions. To mitigate the negative transfer problem, GraphBridge merges the source model with a concurrently trained model, thereby reducing the source bias when applied to the target domain. Our method is thoroughly evaluated across diverse transfer learning scenarios, including Graph2Graph, Node2Node, Graph2Node, and graph2point-cloud. Empirical validation, conducted over 16 datasets representative of these scenarios, confirms the framework's capacity for task- and domain-agnostic transfer learning within graph-like data, marking a significant advancement in the field of GNNs. Code is available at https://github.com/jujulili888/GraphBridge.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 45 of its 62 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

45 of 62 references.

References · 45

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  3. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  4. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  6. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  8. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  9. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  10. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  11. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  12. 2022A Generalist Agentcited by 808
33 more
  1. 2015Image-based Recommendations on Styles and Substitutescited by 706
  2. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  3. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 463
  4. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 431
  5. 2021VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Taskscited by 320
  6. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  7. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 303
  8. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  9. 2018The Natural Language Decathlon: Multitask Learning as Question Answeringcited by 236
  10. 2022LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learningcited by 230
  11. 2019Universally Slimmable Networks and Improved Training Techniquescited by 221
  12. 2018Multi-Adversarial Domain Adaptationcited by 196
  13. 2022SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentationcited by 171
  14. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillationcited by 152
  15. 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 148
  16. 2020Distilling Knowledge from Graph Convolutional Networkscited by 129
  17. 2020Self-supervised Learning on Graphs: Deep Insights and New Directioncited by 108
  18. 2022Deep Model Reassemblycited by 78
  19. 2019Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolutioncited by 67
  20. 2022Does GNN Pretraining Help Molecular Representation?cited by 60
  21. 2021Graph-Free Knowledge Distillation for Graph Neural Networkscited by 46
  22. 2020Adversarial Deep Network Embedding for Cross-network Node Classificationcited by 44
  23. 2019DANE: Domain Adaptive Network Embeddingcited by 43
  24. 2021Graph Domain Adaptation: A Generative Viewcited by 35
  25. 2022MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initializationcited by 31
  26. 2022Learning Graph Neural Networks for Image Style Transfercited by 29
  27. 2021Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networkscited by 25
  28. 2018Domain Adaptation on Graphs by Learning Aligned Graph Basescited by 24
  29. 2023Deep Graph Reprogrammingcited by 22
  30. 2020Finding Patient Zero: Learning Contagion Source with Graph Neural Networkscited by 15
  31. 2023Towards Robust and Accurate Visual Promptingcited by 5
  32. 2024Encapsulating Knowledge in One Promptcited by 3
  33. 2018Domain Adaptation on Graphs by Learning Graph Topologies: Theoretical Analysis and an Algorithmcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025SA2GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentationcited by 5
  2. 2026GUIDED Network-Agnostic Feature Initialization for Spatial Transferability in GNN-based Modelscited by 0
  3. 2026Graph Domain Adaptation Does Not End with Representation Learningcited by 0
  4. 2026Revisiting the Generalization of Neural Graph Edit Distance Modelscited by 0