Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
The message-passing paradigm has served as the foundation of graph neural networks (GNNs) for years, making them achieve great success in a wide range of applications. Despite its elegance, this paradigm presents several unexpected challenges for graph-level tasks, such as the long-range problem, information bottleneck, over-squashing phenomenon, and limited expressivity. In this study, we aim to overcome these major challenges and break the conventional "node- and edge-centric" mindset in graph-level tasks. To this end, we provide an in-depth theoretical analysis of the causes of the information bottleneck from the perspective of information influence. Building on the theoretical results, we offer unique insights to break this bottleneck and suggest extracting a skeleton tree from the original graph, followed by propagating information in a distinctive manner on this tree. Drawing inspiration from natural trees, we further propose to find trunks from graph skeleton trees to create powerful graph representations and develop the corresponding framework for graph-level tasks. Extensive experiments on multiple real-world datasets demonstrate the superiority of our model. Comprehensive experimental analyses further highlight its capability of capturing long-range dependencies and alleviating the over-squashing problem, thereby providing novel insights into graph-level tasks.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TPAMI.2023.3336315 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Dynamic hypergraph representation for bone metastasis analysis.
Comput Methods Programs Biomed
November 2025
Department of Pathology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, 510080, Guangdong, China. Electronic address:
Background And Objective: Bone metastasis cancer analysis is a significant challenge in pathology and plays a critical role in determining patient quality of life and treatment strategies. The microenvironment and specific tissue structures are essential for pathologists to predict the primary bone cancer origins and primary bone cancer subtyping. By digitizing bone tissue sections into whole slide images (WSIs) and leveraging deep learning to model slide embeddings, this analysis can be enhanced.
View Article and Find Full Text PDFFingerprint-enhanced hierarchical molecular graph neural networks for property prediction.
J Pharm Anal
June 2025
Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR, 999078, China.
Accurate prediction of molecular properties is crucial for selecting compounds with ideal properties and reducing the costs and risks of trials. Traditional methods based on manually crafted features and graph-based methods have shown promising results in molecular property prediction. However, traditional methods rely on expert knowledge and often fail to capture the complex structures and interactions within molecules.
View Article and Find Full Text PDFAn enhancement of multi-scope topological graph pooling and representation learning with attention for molecular graph classification.
Comput Biol Chem
December 2025
Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Vietnam. Electronic address:
In recent years, recent advancements have shown the successful integration of topological data analysis (TDA) with deep learning (DL) to enhance representations of complex data structures, such as graphs. Graph neural networks (GNNs) have emerged as a powerful tool for analyzing graph-based data and have been popularly applied to multiple tasks related to node and graph analysis and classification. Given the intrinsic topological nature of graph connectivity, recent studies have leveraged topological features; including persistent homology and landmark extraction, to enrich graph representations.
View Article and Find Full Text PDFAn end-to-end attention-based approach for learning on graphs.
Nat Commun
June 2025
Department of Computer Science and Technology, University of Cambridge, Cambridge, UK.
There has been a recent surge in transformer-based architectures for learning on graphs, mainly motivated by attention as an effective learning mechanism and the desire to supersede the hand-crafted operators characteristic of message passing schemes. However, concerns over their empirical effectiveness, scalability, and complexity of the pre-processing steps have been raised, especially in relation to much simpler graph neural networks that typically perform on par with them across a wide range of benchmarks. To address these shortcomings, we consider graphs as sets of edges and propose a purely attention-based approach consisting of an encoder and an attention pooling mechanism.
View Article and Find Full Text PDFCross-view self-supervised heterogeneous graph representation learning.
Neural Netw
October 2025
College of Information Technology, Shanghai Ocean University, Shanghai, PR China. Electronic address:
Heterogeneous graph neural networks (HGNNs) often face challenges in efficiently integrating information from multiple views, which hinders their ability to fully leverage complex data structures. To overcome this problem, we present an improved graph-level cross-attention mechanism specifically designed to enhance multi-view integration and improve the model's expressiveness in heterogeneous networks. By incorporating random walks, the Katz index, and Transformers, the model captures higher-order semantic relationships between nodes within the meta-path view.
View Article and Find Full Text PDF