REVIEW 12 cited by
Graph Foundation Models: Concepts, Opportunities and Challenges
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
Foundation models have emerged as critical components in a variety of artificial intelligence applications, and showcase significant success in natural language processing and several other domains. Meanwhile, the field of graph machine learning is witnessing a paradigm transition from shallow methods to more sophisticated deep learning approaches. The capabilities of foundation models in generalization and adaptation motivate graph machine learning researchers to discuss the potential of developing a new graph learning paradigm. This paradigm envisions models that are pre-trained on extensive graph data and can be adapted for various graph tasks. Despite this burgeoning interest, there is a noticeable lack of clear definitions and systematic analyses pertaining to this new domain. To this end, this article introduces the concept of Graph Foundation Models (GFMs), and offers an exhaustive explanation of their key characteristics and underlying technologies. We proceed to classify the existing work related to GFMs into three distinct categories, based on their dependence on graph neural networks and large language models. In addition to providing a thorough review of the current state of GFMs, this article also outlooks potential avenues for future research in this rapidly evolving domain.
Forward citations
Cited by 12 Pith papers
-
PhyCheck: Fine-Grained Evidence-Grounded Dataset for Physical Law Understanding in Video-LLMs
PhyCheck is a 69,825-pair video QA benchmark that tests and improves Video-LLMs' ability to judge whether events obey physical laws, with fine-grained evidence questions and a context-sensitivity pilot.
-
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.
-
Semi-Supervised Text-Attributed Graph Distillation
STAD distills large text-attributed graphs into tiny human-readable graphs that match or beat full-graph semi-supervised node classification.
-
GraphLAMA: Enabling Efficient Adaptation of Graph Language Models with Limited Annotations
A frozen-LLM graph model with a small tuned adapter (about 726k parameters, 3MB) outperforms in-context learning and instruction-tuned graph LLMs in few/zero-shot node classification and summary generation.
-
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.
-
MEGA-CL: A Molecular Foundation Model for Generalizable ADMET Prediction through Graph External Attention and Contrastive Learning
A contrastive GNN with external attention, pre-trained on ~100M molecules, improves multi-task ADMET prediction and shows prospective wet-lab agreement on three compounds.
-
A Weisfeiler-Leman Characterization of Global-Attention Graph Transformers for Mixed-Integer Linear Programs
Global-attention MILP graph encoders built from symmetric multiset aggregation are 1-WL-bounded: 1-WL-equivalent MILP graphs always get identical embeddings.
-
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.
-
Masked Language Models are Good Heterogeneous Graph Generalizers
A masked language model fine-tuned on metapath-derived text and cloze-style task templates transfers across heterogeneous graph datasets better than HGNN and LLM baselines, though link prediction results are compromis...
-
OpenGT: A Comprehensive Benchmark For Graph Transformers
OpenGT benchmarks 16 graph models on 14 datasets, finding graph transformers excel on heterophilous graphs, though several observations are not robustly supported.
-
RankGraph: Unified Heterogeneous Graph Learning for Cross-Domain Recommendation
RankGraph combines RGCN-style message passing, contrastive learning, and graph-token injection into foundation-model recommenders, reporting small online CTR and CVR gains.
-
Grounding Intelligence in Movement
Movement should be treated as a first-class AI modeling modality, and a unified, biomechanically grounded movement foundation model built from aggregated data across species and sensors is the proposed path forward.
Discussion (0). Sign in to comment.