GraphFM: A Scalable Framework for Multi-Graph Pretraining
- URL: http://arxiv.org/abs/2407.11907v1
- Date: Tue, 16 Jul 2024 16:51:43 GMT
- Title: GraphFM: A Scalable Framework for Multi-Graph Pretraining
- Authors: Divyansha Lachi, Mehdi Azabou, Vinam Arora, Eva Dyer,
- Abstract summary: We introduce a scalable multi-graph multi-task pretraining approach specifically tailored for node classification tasks across diverse graph datasets from different domains.
We demonstrate the efficacy of our approach by training a model on 152 different graph datasets comprising over 7.4 million nodes and 189 million edges.
Our results show that pretraining on a diverse array of real and synthetic graphs improves the model's adaptability and stability, while performing competitively with state-of-the-art specialist models.
- Score: 2.882104808886318
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Graph neural networks are typically trained on individual datasets, often requiring highly specialized models and extensive hyperparameter tuning. This dataset-specific approach arises because each graph dataset often has unique node features and diverse connectivity structures, making it difficult to build a generalist model. To address these challenges, we introduce a scalable multi-graph multi-task pretraining approach specifically tailored for node classification tasks across diverse graph datasets from different domains. Our method, Graph Foundation Model (GraphFM), leverages a Perceiver-based encoder that employs learned latent tokens to compress domain-specific features into a common latent space. This approach enhances the model's ability to generalize across different graphs and allows for scaling across diverse data. We demonstrate the efficacy of our approach by training a model on 152 different graph datasets comprising over 7.4 million nodes and 189 million edges, establishing the first set of scaling laws for multi-graph pretraining on datasets spanning many domains (e.g., molecules, citation and product graphs). Our results show that pretraining on a diverse array of real and synthetic graphs improves the model's adaptability and stability, while performing competitively with state-of-the-art specialist models. This work illustrates that multi-graph pretraining can significantly reduce the burden imposed by the current graph training paradigm, unlocking new capabilities for the field of graph neural networks by creating a single generalist model that performs competitively across a wide range of datasets and tasks.
Related papers
- Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models [32.46165651743604]
We propose UniAug, a universal graph structure augmentor built on a diffusion model.
We first pre-train a discrete diffusion model on thousands of graphs across domains to learn the graph structural patterns.
In the downstream phase, we provide adaptive enhancement by conducting graph structure augmentation with the help of the pre-trained diffusion model.
arXiv Detail & Related papers (2024-06-04T02:04:09Z) - OpenGraph: Towards Open Graph Foundation Models [20.401374302429627]
We develop a general graph foundation model to understand the complex topological patterns present in diverse graph data.
We propose a unified graph tokenizer to adapt our graph model to generalize well on unseen graph data.
We also develop a scalable graph transformer, which effectively captures node-wise dependencies within the global topological context.
arXiv Detail & Related papers (2024-03-02T08:05:03Z) - UniGraph: Learning a Cross-Domain Graph Foundation Model From Natural
Language [41.722898353772656]
We present our UniGraph framework, designed to train a graph foundation model capable of generalizing to unseen graphs and tasks across diverse domains.
We propose a cascaded architecture of Language Models (LMs) and Graph Neural Networks (GNNs) as backbone networks with a self-supervised training objective based on Masked Graph Modeling (MGM)
Our comprehensive experiments across various graph learning tasks and domains demonstrate the model's effectiveness in self-supervised representation learning on unseen graphs, few-shot in-context transfer, and zero-shot transfer.
arXiv Detail & Related papers (2024-02-21T09:06:31Z) - GraphControl: Adding Conditional Control to Universal Graph Pre-trained
Models for Graph Domain Transfer Learning [28.04023419006392]
Graph self-supervised algorithms have achieved significant success in acquiring generic knowledge from abundant unlabeled graph data.
Different graphs, even across seemingly similar domains, can differ significantly in terms of attribute semantics.
We introduce an innovative deployment module coined as GraphControl, motivated by ControlNet, to realize better graph domain transfer learning.
arXiv Detail & Related papers (2023-10-11T10:30:49Z) - One for All: Towards Training One Graph Model for All Classification Tasks [61.656962278497225]
A unified model for various graph tasks remains underexplored, primarily due to the challenges unique to the graph learning domain.
We propose textbfOne for All (OFA), the first general framework that can use a single graph model to address the above challenges.
OFA performs well across different tasks, making it the first general-purpose across-domains classification model on graphs.
arXiv Detail & Related papers (2023-09-29T21:15:26Z) - GraphGLOW: Universal and Generalizable Structure Learning for Graph
Neural Networks [72.01829954658889]
This paper introduces the mathematical definition of this novel problem setting.
We devise a general framework that coordinates a single graph-shared structure learner and multiple graph-specific GNNs.
The well-trained structure learner can directly produce adaptive structures for unseen target graphs without any fine-tuning.
arXiv Detail & Related papers (2023-06-20T03:33:22Z) - Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit
Diversity Modeling [60.0185734837814]
Graph neural networks (GNNs) have found extensive applications in learning from graph data.
To bolster the generalization capacity of GNNs, it has become customary to augment training graph structures with techniques like graph augmentations.
This study introduces the concept of Mixture-of-Experts (MoE) to GNNs, with the aim of augmenting their capacity to adapt to a diverse range of training graph structures.
arXiv Detail & Related papers (2023-04-06T01:09:36Z) - GrannGAN: Graph annotation generative adversarial networks [72.66289932625742]
We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton.
The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases.
In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features.
arXiv Detail & Related papers (2022-12-01T11:49:07Z) - Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data.
We present a novel Graph Matching based GNN Pre-Training framework, called GMPT.
The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
arXiv Detail & Related papers (2022-03-03T09:53:53Z) - GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training [62.73470368851127]
Graph representation learning has emerged as a powerful technique for addressing real-world problems.
We design Graph Contrastive Coding -- a self-supervised graph neural network pre-training framework.
We conduct experiments on three graph learning tasks and ten graph datasets.
arXiv Detail & Related papers (2020-06-17T16:18:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.