mlsanityData to 7 Oct 2026

Boosting Graph Foundation Model from Structural Perspective

arXiv 2407.19941 ↗First posted 29 Jul 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph foundation models have recently attracted significant attention due to its strong generalizability. Although existing methods resort to language models to learn unified semantic representations across domains, they disregard the unique structural characteristics of graphs from different domains. To address the problem, in this paper, we boost graph foundation model from structural perspective and propose BooG. The model constructs virtual super nodes to unify structural characteristics of graph data from different domains. Specifically, the super nodes fuse the information of anchor nodes and class labels, where each anchor node captures the information of a node or a graph instance to be classified. Instead of using the raw graph structure, we connect super nodes to all nodes within their neighborhood by virtual edges. This new structure allows for effective information aggregation while unifying cross-domain structural characteristics. Additionally, we propose a novel pre-training objective based on contrastive learning, which learns more expressive representations for graph data and generalizes effectively to different domains and downstream tasks. Experimental results on various datasets and tasks demonstrate the superior performance of BooG. We provide our code and data here: https://anonymous.4open.science/r/BooG-EE42/.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 68 references that are in the map. First posted on arXiv 29 Jul 2024.

Builds on

37 of 68 references.

References · 37

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2019Simplifying Graph Convolutional Networkscited by 1,470
  10. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  11. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  12. 2018Deep Graph Infomaxcited by 1,101
25 more
  1. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  2. 2018Link Prediction Based on Graph Neural Networkscited by 829
  3. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  4. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 461
  5. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  6. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
  7. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 302
  8. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 253
  9. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 239
  10. 2020Graph Neural Networks with Heterophilycited by 202
  11. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  12. 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 166
  13. 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 147
  14. 2017Predicting multicellular function through multi-layer tissue networkscited by 138
  15. 2023Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learningcited by 132
  16. 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
  17. 2024ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphscited by 83
  18. 2024OpenGraph: Towards Open Graph Foundation Modelscited by 75
  19. 2023GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learningcited by 70
  20. 2022Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminatingcited by 57
  21. 2021Automated Self-Supervised Learning for Graphscited by 50
  22. 2021Block Modeling-Guided Graph Convolutional Neural Networkscited by 32
  23. 2024A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directionscited by 13
  24. 2023Graph-Segmenter: Graph Transformer with Boundary-aware Attention for Semantic Segmentationcited by 6
  25. 2021Combat Data Shift in Few-shot Learning with Knowledge Graphcited by 2

Built on by

Not cited yet.