REVIEW 5 cited by
Position: Graph Foundation Models are Already Here
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
Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain, aiming to develop graph models trained on extensive and diverse data to enhance their applicability across various tasks and domains. Developing GFMs presents unique challenges over traditional Graph Neural Networks (GNNs), which are typically trained from scratch for specific tasks on particular datasets. The primary challenge in constructing GFMs lies in effectively leveraging vast and diverse graph data to achieve positive transfer. Drawing inspiration from existing foundation models in the CV and NLP domains, we propose a novel perspective for the GFM development by advocating for a ``graph vocabulary'', in which the basic transferable units underlying graphs encode the invariance on graphs. We ground the graph vocabulary construction from essential aspects including network analysis, expressiveness, and stability. Such a vocabulary perspective can potentially advance the future GFM design in line with the neural scaling laws. All relevant resources with GFM design can be found here.
Forward citations
Cited by 5 Pith papers
-
Attacking Graph Foundation Models Through Their Shared Representation
A shared representation layer in graph foundation models is a distinct attack surface: input edits break three of six models and one spectral tokenizer is uniquely fragile.
-
Canopy: A Heterograph Foundation Model for Metabolic Engineering
Frozen embeddings from a pretrained heterogeneous graph transformer over a 6.9M-node metabolic-engineering knowledge graph predict fermentation titers at R²=0.41, outperforming tabular baselines (R²=0.24).
-
IOHunter: Graph Foundation Model to Uncover Online Information Operations
IOHunter detects information-operation drivers by fusing frozen language-model text embeddings with a GNN over a fused user-similarity network, reporting SOTA Macro-F1 on six Twitter IO datasets and cross-country tran...
-
One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs
OMOG trains a bank of per-graph GNN experts and fuses the top-ranked experts for each test graph, reporting gains in zero-shot and few-shot graph transfer.
-
path_boost: A Python Package for Interpretable Graph-Level Prediction using Path-Based Gradient Boosting
path_boost packages PathBoost, an interpretable path-based gradient booster for graphs that is competitive with GINE and WL+SVR on six molecular regression datasets while exposing which labeled paths drive predictions.
Discussion (0). Continue with ORCID to comment.