REVIEW 7 cited by
Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Given the ubiquity of graph data, it is intriguing to ask: Is it possible to train a graph foundation model on a broad range of graph data across diverse domains? A major hurdle toward this goal lies in the fact that graphs from different domains often exhibit profoundly divergent characteristics. Although there have been some initial efforts in integrating multi-domain graphs for pre-training, they primarily rely on textual descriptions to align the graphs, limiting their application to text-attributed graphs. Moreover, different source domains may conflict or interfere with each other, and their relevance to the target domain can vary significantly. To address these issues, we propose MDGPT, a text free Multi-Domain Graph Pre-Training and adaptation framework designed to exploit multi-domain knowledge for graph learning. First, we propose a set of domain tokens to to align features across source domains for synergistic pre-training. Second, we propose a dual prompts, consisting of a unifying prompt and a mixing prompt, to further adapt the target domain with unified multi-domain knowledge and a tailored mixture of domain-specific knowledge. Finally, we conduct extensive experiments involving six public datasets to evaluate and analyze MDGPT, which outperforms prior art by up to 37.9%.
Forward citations
Cited by 7 Pith papers
-
Beyond Feature and Structure Alignment: Learning Transferable Propagation Knowledge for Graph Foundation Models
ProGFM transfers graph knowledge across domains by learning a prototype bank of per-edge, per-dimension propagation strengths and using them to modulate message passing on unseen graphs.
-
CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer
CHARM improves zero-shot transfer on multimodal product graphs by replacing raw nodes with hierarchical semantic contexts and modality-complementary bridges that are encoded as LLM-readable tokens.
-
GCoT: Chain-of-Thought Prompt Learning for Graphs
GCoT improves few-shot graph classification by iteratively generating node-specific prompts from intermediate encoder states, mimicking chain-of-thought reasoning for text-free graphs.
-
Dynamic Graph Prompting via Topology-Routed Mixed-Curvature Experts
CurvPrompt introduces topology-routed mixed-curvature experts for dynamic graph prompting, improving few-shot link prediction and node classification over fixed-geometry baselines.
-
What Makes Graph Unified? Principles and Generative Sliding-Window Transformer for Graph Foundation Models
Ordering node features by topological smoothness and encoding them with a shared sliding-window transformer plus reconstruction yields transferable cross-domain graph representations without fine-tuning.
-
Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding
GPH^2 pre-trains one expert per graph on edge-dropped or meta-path views and fuses frozen experts with class-wise attention, outperforming type-specific graph pre-training baselines.
-
SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation
A text-free graph foundation model uses per-domain structure tokens and dual prompts to align structural differences across domains, improving few-shot cross-domain node and graph classification.
Discussion (0). Continue with ORCID to comment.