English
Related papers

Related papers: Commute-Time-Optimised Graphs for GNNs

200 papers

Graph neural networks (GNNs) have exhibited state-of-the-art performance across wide-range of domains such as recommender systems, material design, and drug repurposing. Yet message-passing GNNs suffer from over-squashing -- exponential…

Machine Learning · Computer Science 2025-08-14 Danial Saber , Amirali Salehi-Abari

Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compressed, and…

Machine Learning · Computer Science 2026-05-05 Hugo Attali , Nathalie Pernelle , Davide Buscaldi , Fragkiskos D. Malliaros

Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compressed, and…

Machine Learning · Computer Science 2026-05-04 Hugo Attali , Davide Buscaldi , Nathalie Pernelle , Fragkiskos D. Malliaros

Graph rewiring has emerged as a key technique to alleviate over-squashing in Graph Neural Networks (GNNs) and Graph Transformers by modifying the graph topology to improve information flow. While effective, rewiring inherently alters the…

Machine Learning · Computer Science 2025-10-24 Alexandre Benoit , Catherine Aitken , Yu He

Graph Neural Networks (GNNs) are popular models for machine learning on graphs that typically follow the message-passing paradigm, whereby the feature of a node is updated recursively upon aggregating information over its neighbors. While…

Machine Learning · Computer Science 2024-05-07 Federico Barbero , Ameya Velingker , Amin Saberi , Michael Bronstein , Francesco Di Giovanni

Evolving relations in real-world networks are often modelled by temporal graphs. Temporal Graph Neural Networks (TGNNs) emerged to model evolutionary behaviour of such graphs by leveraging the message passing primitive at the core of Graph…

Machine Learning · Computer Science 2024-10-23 Katarina Petrović , Shenyang Huang , Farimah Poursafaei , Petar Veličković

Graph Neural Networks (GNNs) have shown remarkable success in learning from graph-structured data. However, their application to directed graphs (digraphs) presents unique challenges, primarily due to the inherent asymmetry in node…

Machine Learning · Computer Science 2025-05-16 Wei Zhuo , Han Yu , Guang Tan , Xiaoxiao Li

Recently there has been much interest in graph-based learning, with applications in collaborative filtering for recommender networks, link prediction for social networks and fraud detection. These networks can consist of millions of…

Social and Information Networks · Computer Science 2012-06-26 Purnamrita Sarkar , Andrew Moore

Graph neural networks compute node representations by performing multiple message-passing steps that consist in local aggregations of node features. Having deep models that can leverage longer-range interactions between nodes is hindered by…

Machine Learning · Computer Science 2025-06-27 Alessio Micheli , Domenico Tortorella

Graph Neural Networks (GNNs) are popular machine learning methods for modeling graph data. A lot of GNNs perform well on homophily graphs while having unsatisfactory performance on heterophily graphs. Recently, some researchers turn their…

Machine Learning · Computer Science 2022-09-20 Wendong Bi , Lun Du , Qiang Fu , Yanlin Wang , Shi Han , Dongmei Zhang

Maximizing the spectral gap through graph rewiring has been proposed to enhance the performance of message-passing graph neural networks (GNNs) by addressing over-squashing. However, as we show, minimizing the spectral gap can also improve…

Machine Learning · Computer Science 2025-02-10 Celia Rubio-Madrigal , Adarsh Jamadandi , Rebekka Burkholz

Graph Neural Networks (GNNs) have been shown to achieve competitive results to tackle graph-related tasks, such as node and graph classification, link prediction and node and graph clustering in a variety of domains. Most GNNs use a message…

Machine Learning · Computer Science 2023-03-07 Adrian Arnaiz-Rodriguez , Ahmed Begga , Francisco Escolano , Nuria Oliver

As powerful tools for representation learning on graphs, graph neural networks (GNNs) have facilitated various applications from drug discovery to recommender systems. Nevertheless, the effectiveness of GNNs is immensely challenged by…

Machine Learning · Computer Science 2023-02-28 Wei Jin , Tong Zhao , Jiayuan Ding , Yozen Liu , Jiliang Tang , Neil Shah

We consider a setting where multiple entities inter-act with each other over time and the time-varying statuses of the entities are represented as multiple correlated time series. For example, speed sensors are deployed in different…

Machine Learning · Computer Science 2021-03-23 Razvan-Gabriel Cirstea , Chenjuan Guo , Bin Yang

Message passing neural networks (MPNNs) have been shown to suffer from the phenomenon of over-squashing that causes poor performance for tasks relying on long-range interactions. This can be largely attributed to message passing only…

Machine Learning · Computer Science 2023-05-19 Benjamin Gutteridge , Xiaowen Dong , Michael Bronstein , Francesco Di Giovanni

We study how we can accelerate the spreading of information in temporal graphs via shifting operations; a problem that captures real-world applications varying from information flows to distribution schedules. In a temporal graph there is a…

Data Structures and Algorithms · Computer Science 2025-10-09 Argyrios Deligkas , Eduard Eiben , George Skretas

Graph condensation (GC) aims to distill the original graph into a small-scale graph, mitigating redundancy and accelerating GNN training. However, conventional GC approaches heavily rely on rigid GNNs and task-specific supervision. Such a…

Machine Learning · Computer Science 2025-09-19 Yeyu Yan , Shuai Zheng , Wenjun Hui , Xiangkai Zhu , Dong Chen , Zhenfeng Zhu , Yao Zhao , Kunlun He

Mesh-based simulation using Graph Neural Networks (GNNs) has been recognized as a promising approach for modeling fluid dynamics. However, the mesh refinement techniques which allocate finer resolution to regions with steep gradients can…

Machine Learning · Computer Science 2025-11-18 Sangwoo Seo , Hyunsung Kim , Jiwan Kim , Chanyoung Park

Within many real-world networks the links between pairs of nodes change over time. Thus, there has been a recent boom in studying temporal graphs. Recognizing patterns in temporal graphs requires a proximity measure to compare different…

Machine Learning · Computer Science 2020-07-07 Vincent Froese , Brijnesh Jain , Rolf Niedermeier , Malte Renken

Information over-squashing is a phenomenon of inefficient information propagation between distant nodes on networks. It is an important problem that is known to significantly impact the training of graph neural networks (GNNs), as the…

Machine Learning · Statistics 2022-07-19 Jakub Bober , Anthea Monod , Emil Saucan , Kevin N. Webster
‹ Prev 1 2 3 10 Next ›