English
Related papers

Related papers: When Do Graph Foundation Models Transfer? A Data-C…

200 papers

Graph neural networks (GNNs) have become powerful tools for processing graph-based information in various domains. A desirable property of GNNs is transferability, where a trained network can swap in information from a different graph…

Machine Learning · Computer Science 2024-06-24 A. Martina Neuman , Jason J. Bramburger

Graph neural networks (GNNs), consisting of a cascade of layers applying a graph convolution followed by a pointwise nonlinearity, have become a powerful architecture to process signals supported on graphs. Graph convolutions (and thus,…

Machine Learning · Computer Science 2019-10-23 Fernando Gama , Joan Bruna , Alejandro Ribeiro

Graphs are a fundamental data structure for representing relational information in domains such as social networks, molecular systems, and knowledge graphs. However, graph learning models often suffer from limited generalization when…

Machine Learning · Computer Science 2026-01-30 Haoyang Li , Haibo Chen , Xin Wang , Wenwu Zhu

We present Graph Foundation Models (GFMs) which have made significant progress in various tasks, but their robustness against domain noise, structural perturbations, and adversarial attacks remains underexplored. A key limitation is the…

Machine Learning · Computer Science 2026-03-11 Junhua Shi , Qingyun Sun , Haonan Yuan , Xingcheng Fu

The pretrain-transfer paradigm, which underpins the success of large language models (LLMs), has demonstrated the immense power of creating foundation models that learn generalizable representations from vast datasets. However, extending…

Machine Learning · Computer Science 2025-09-30 Yunhao Liang , Pujun Zhang , Yuan Qu , Shaochong Lin , Zuo-jun Max Shen

We study spectral graph convolutional neural networks (GCNNs), where filters are defined as continuous functions of the graph shift operator (GSO) through functional calculus. A spectral GCNN is not tailored to one specific graph and can be…

Machine Learning · Computer Science 2022-06-28 Sohir Maskey , Ron Levie , Gitta Kutyniok

This paper introduces a design method for densergraph-frequency graph Fourier frames (DGFFs) to enhance graph signal processing and analysis. The graph Fourier transform (GFT) enables us to analyze graph signals in the graph spectral domain…

Signal Processing · Electrical Eng. & Systems 2025-03-18 Kaito Nitani , Seisuke Kyochi

The foundation model has heralded a new era in artificial intelligence, pretraining a single model to offer cross-domain transferability on different datasets. Graph neural networks excel at learning graph data, the omnipresent…

Machine Learning · Computer Science 2025-04-09 Li Sun , Zhenhao Huang , Suyang Zhou , Qiqi Wan , Hao Peng , Philip Yu

Graph neural networks (GNNs) have achieved remarkable success in various domains, yet they often struggle with domain adaptation due to significant structural distribution shifts and insufficient exploration of transferable patterns. One of…

Machine Learning · Computer Science 2025-10-16 Haoyu Zhang , Yuxuan Cheng , Wenqi Fan , Yulong Chen , Yifan Zhang

Graph foundation models face several fundamental challenges including transferability across datasets and data scarcity, which calls into question the very feasibility of graph foundation models. However, despite similar challenges, the…

Machine Learning · Computer Science 2026-02-13 Dmitry Eremeev , Oleg Platonov , Gleb Bazhenov , Artem Babenko , Liudmila Prokhorenkova

Graph neural networks (GNNs) achieve strong performance on graph learning tasks, but training on large-scale networks remains computationally challenging. Transferability results show that GNNs with fixed weights can generalize from smaller…

Signal Processing · Electrical Eng. & Systems 2026-04-17 Haoyu Wang , Renyuan Ma , Gonzalo Mateos , Luana Ruiz

Graph-structured data underpins many critical applications. While foundation models have transformed language and vision via large-scale pretraining and lightweight adaptation, extending this paradigm to general, real-world graphs is…

Machine Learning · Computer Science 2026-05-22 Maya Bechler-Speicher , Yoel Gottlieb , Andrey Isakov , David Abensur , Ami Tavory , Daniel Haimovich , Ido Guy , Udi Weinsberg

Graph neural networks (GNNs) have emerged as a powerful tool for nonlinear processing of graph signals, exhibiting success in recommender systems, power outage prediction, and motion planning, among others. GNNs consists of a cascade of…

Machine Learning · Computer Science 2020-12-02 Fernando Gama , Joan Bruna , Alejandro Ribeiro

As Graph Neural Networks (GNNs) become more pervasive, it becomes paramount to build reliable tools for explaining their predictions. A core desideratum is that explanations are \textit{faithful}, \ie that they portray an accurate picture…

Machine Learning · Computer Science 2025-04-11 Steve Azzolin , Antonio Longa , Stefano Teso , Andrea Passerini

Dynamic graphs are ubiquitous in real-world systems, and building generalizable dynamic Graph Foundation Models has become a frontier in graph learning. However, dynamic graphs from different domains pose fundamental challenges to unified…

Machine Learning · Computer Science 2026-05-14 Haonan Yuan , Qingyun Sun , Junhua Shi , Xingcheng Fu , Jianxin Li , Philip S. Yu

Foundation models are pretrained on large-scale corpora to learn generalizable patterns across domains and tasks -- such as contours, textures, and edges in images, or tokens and sentences in text. In contrast, discovering such generalities…

Machine Learning · Computer Science 2025-05-27 Zehong Wang , Zheyuan Zhang , Tianyi Ma , Nitesh V Chawla , Chuxu Zhang , Yanfang Ye

The growing interests and applications of graph learning in diverse domains have propelled the development of a unified model generalizing well across different graphs and tasks, known as the Graph Foundation Model (GFM). Existing research…

Machine Learning · Computer Science 2025-06-17 Trung-Kien Nguyen , Heng Ping , Shixuan Li , Peiyu Zhang , Nikos Kanakaris , Nicholas Kotov , Paul Bogdan

Graph Neural Networks (GNNs) have shown remarkable performance on graph-structured data. However, recent empirical studies suggest that GNNs are very susceptible to distribution shift. There is still significant ambiguity about why…

Machine Learning · Computer Science 2023-06-07 Qi Zhu , Yizhu Jiao , Natalia Ponomareva , Jiawei Han , Bryan Perozzi

Graph Neural Networks (GNNs) are information processing architectures for signals supported on graphs. They are presented here as generalizations of convolutional neural networks (CNNs) in which individual layers contain banks of graph…

Machine Learning · Computer Science 2021-02-01 Luana Ruiz , Fernando Gama , Alejandro Ribeiro

Graph neural networks (GNNs) provide state-of-the-art results in a wide variety of tasks which typically involve predicting features at the vertices of a graph. They are built from layers of graph convolutions which serve as a powerful…

Machine Learning · Statistics 2024-11-08 Mauricio Velasco , Kaiying O'Hare , Bernardo Rychtenberg , Soledad Villar