Graph Positional and Structural Encoder
- URL: http://arxiv.org/abs/2307.07107v2
- Date: Mon, 10 Jun 2024 21:36:14 GMT
- Title: Graph Positional and Structural Encoder
- Authors: Semih Cantürk, Renming Liu, Olivier Lapointe-Gagné, Vincent Létourneau, Guy Wolf, Dominique Beaini, Ladislav Rampášek,
- Abstract summary: We present the first-ever graph encoder designed to capture rich PSE representations for augmenting any GNN.
GPSE learns an efficient common latent representation for multiple PSEs, and is highly transferable.
We show that GPSE-enhanced models can significantly outperform those that employ explicitly computed PSEs, and at least match their performance in others.
- Score: 11.647944336315346
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Positional and structural encodings (PSE) enable better identifiability of nodes within a graph, rendering them essential tools for empowering modern GNNs, and in particular graph Transformers. However, designing PSEs that work optimally for all graph prediction tasks is a challenging and unsolved problem. Here, we present the Graph Positional and Structural Encoder (GPSE), the first-ever graph encoder designed to capture rich PSE representations for augmenting any GNN. GPSE learns an efficient common latent representation for multiple PSEs, and is highly transferable: The encoder trained on a particular graph dataset can be used effectively on datasets drawn from markedly different distributions and modalities. We show that across a wide range of benchmarks, GPSE-enhanced models can significantly outperform those that employ explicitly computed PSEs, and at least match their performance in others. Our results pave the way for the development of foundational pre-trained graph encoders for extracting positional and structural information, and highlight their potential as a more powerful and efficient alternative to explicitly computed PSEs and existing self-supervised pre-training approaches. Our framework and pre-trained models are publicly available at https://github.com/G-Taxonomy-Workgroup/GPSE. For convenience, GPSE has also been integrated into the PyG library to facilitate downstream applications.
Related papers
- Learning Efficient Positional Encodings with Graph Neural Networks [109.8653020407373]
We introduce PEARL, a novel framework of learnable PEs for graphs.
PEARL approximates equivariant functions of eigenvectors with linear complexity, while rigorously establishing its stability and high expressive power.
Our analysis demonstrates that PEARL approximates equivariant functions of eigenvectors with linear complexity, while rigorously establishing its stability and high expressive power.
arXiv Detail & Related papers (2025-02-03T07:28:53Z) - Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs)
This framework provides a standardized setting to evaluate GNNs across diverse datasets.
We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
arXiv Detail & Related papers (2025-01-01T08:48:53Z) - Towards Graph Foundation Models: A Study on the Generalization of Positional and Structural Encodings [36.58861528662219]
positional and structural encodings (PSEs) have been integrated into graph neural networks (GNNs)
This paper investigates the fine-tuning efficiency, scalability with sample size, generalization and capability of learnable PSEs across diverse graph datasets.
arXiv Detail & Related papers (2024-12-10T10:58:47Z) - Range-aware Positional Encoding via High-order Pretraining: Theory and Practice [14.521929085104441]
Unsupervised pre-training on vast amounts of graph data is critical in real-world applications wherein labeled data is limited.
We propose a novel pre-training strategy on graphs that focuses on modeling their multi-resolution structural information.
Our approach relies solely on the graph structure, it is also domain-agnostic and adaptable to datasets from various domains.
arXiv Detail & Related papers (2024-09-27T19:53:10Z) - Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation [31.106636947179005]
Unsupervised Graph Domain Adaptation involves the transfer of knowledge from a label-rich source graph to an unlabeled target graph.
We present the first comprehensive benchmark for unsupervised graph domain adaptation named GDABench.
We observe that the performance of current UGDA models varies significantly across different datasets and adaptation scenarios.
arXiv Detail & Related papers (2024-07-09T06:44:09Z) - MentorGNN: Deriving Curriculum for Pre-Training GNNs [61.97574489259085]
We propose an end-to-end model named MentorGNN that aims to supervise the pre-training process of GNNs across graphs.
We shed new light on the problem of domain adaption on relational data (i.e., graphs) by deriving a natural and interpretable upper bound on the generalization error of the pre-trained GNNs.
arXiv Detail & Related papers (2022-08-21T15:12:08Z) - GraphiT: Encoding Graph Structure in Transformers [37.33808493548781]
We show that viewing graphs as sets of node features and structural and positional information is able to outperform representations learned with classical graph neural networks (GNNs)
Our model, GraphiT, encodes such information by (i) leveraging relative positional encoding strategies in self-attention scores based on positive definite kernels on graphs, and (ii) enumerating and encoding local sub-structures such as paths of short length.
arXiv Detail & Related papers (2021-06-10T11:36:22Z) - Robust Optimization as Data Augmentation for Large-scale Graphs [117.2376815614148]
We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training.
FLAG is a general-purpose approach for graph data, which universally works in node classification, link prediction, and graph classification tasks.
arXiv Detail & Related papers (2020-10-19T21:51:47Z) - 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) - Heuristic Semi-Supervised Learning for Graph Generation Inspired by
Electoral College [80.67842220664231]
We propose a novel pre-processing technique, namely ELectoral COllege (ELCO), which automatically expands new nodes and edges to refine the label similarity within a dense subgraph.
In all setups tested, our method boosts the average score of base models by a large margin of 4.7 points, as well as consistently outperforms the state-of-the-art.
arXiv Detail & Related papers (2020-06-10T14:48:48Z) - Self-Constructing Graph Convolutional Networks for Semantic Labeling [23.623276007011373]
We propose a novel architecture called the Self-Constructing Graph (SCG), which makes use of learnable latent variables to generate embeddings.
SCG can automatically obtain optimized non-local context graphs from complex-shaped objects in aerial imagery.
We demonstrate the effectiveness and flexibility of the proposed SCG on the publicly available ISPRS Vaihingen dataset.
arXiv Detail & Related papers (2020-03-15T21:55:24Z)
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.