REVIEW 10 cited by
AnyGraph: Graph Foundation Model in the Wild
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
The growing ubiquity of relational data structured as graphs has underscored the need for graph learning models with exceptional generalization capabilities. However, current approaches often struggle to effectively extract generalizable insights, frequently requiring extensive fine-tuning and limiting their versatility. Graph foundation models offer a transformative solution, with the potential to learn robust, generalizable representations from graph data. This enables more effective and adaptable applications across a wide spectrum of tasks and domains. In this work, we investigate a unified graph model, AnyGraph, designed to handle key challenges: i) Structure Heterogenity. Addressing distribution shift in graph structural information; ii) Feature Heterogenity. Handling diverse feature representation spaces across graph datasets; iii) Fast Adaptation. Efficiently adapting the model to new graph domains; iv) Scaling Law Emergence. Enabling the model to exhibit scaling law behavior, where its performance scales favorably with the amount of data and parameter sizes. To tackle these critical challenges, we build the AnyGraph upon a Graph Mixture-of-Experts (MoE) architecture. This approach empowers the model to effectively manage both the in-domain and cross-domain distribution shift concerning structure-level and feature-level heterogeneity. Furthermore, a lightweight graph expert routing mechanism is proposed to facilitate AnyGraph's fast adaptability to new data and domains. Our extensive experiments on diverse 38 graph datasets have demonstrated the strong zero-shot learning performance of AnyGraph across diverse graph domains with significant distribution shift. Furthermore, we have validated the model's fast adaptation ability and scaling law emergence, showcasing its versatility.
Forward citations
Cited by 10 Pith papers
-
When Do Graph Foundation Models Transfer? A Data-Centric Theory
Using graphon limits for dense graphs, the authors decompose cross-domain output shifts for Lipschitz backbones into graph-specific finite-sample terms and a relabeling-invariant domain discrepancy, with stability res...
-
On the Safety of Graph Representation Learning
GRL-Safety benchmark shows that safety in graph representation learning depends on interactions between method design and specific graph stresses rather than broad method families.
-
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.
-
Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework
A federated pretraining-and-prompt-tuning framework that aligns image, text, and graph-topology information across privacy-separated clients claims consistent state-of-the-art results on 12 multimodal graph datasets.
-
FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning
FedLAB organizes multimodal graph knowledge into typed hierarchical codebooks for modality evidence, node semantics, and topology context via federated semantic barycenter pre-training, improving performance by up to ...
-
A Fair Evaluation of Graph Foundation Models for Node Property Prediction
Reevaluation of 9 GFMs shows only recent prior-data fitted network models outperform tuned GNNs on node property prediction, at higher cost.
-
Bridging Input Feature Spaces Towards Graph Foundation Models
ALL-IN projects node features to a random shared space and uses covariance operators to produce representations invariant to input feature permutations and orthogonal transformations, enabling transfer across graph datasets.
-
No Need to Train Your RDB Foundation Model
Column-wise, parameter-free JUICE encodings let single-table ICL models solve multi-table RDB prediction tasks with no training or fine-tuning.
-
Graph Computation Meets Circuit Algebra: A Task-Aligned Analysis of Graph Neural Networks for Electronic Design Automation
GNNs succeed in EDA when their propagation, aggregation, and supervision match the native algebra of each circuit task, such as max-plus recurrences for timing or hypergraph penalties for placement.
-
GSTBench: A Benchmark Study on the Transferability of Graph Self-Supervised Learning
GSTBench finds that masked feature reconstruction (GraphMAE) is the only one of five graph self-supervised pretraining objectives that consistently transfers across eight datasets, while contrastive methods often perf...
Discussion (0). Sign in to comment.