English
Related papers

Related papers: Leave Graphs Alone: Addressing Over-Squashing with…

200 papers

Graph Neural Networks struggle to capture long-range dependencies due to over-squashing, where information from exponentially growing neighborhoods must pass through a small number of structural bottlenecks. While recent rewiring methods…

Machine Learning · Computer Science 2026-03-13 Bertran Miquel-Oliver , Manel Gil-Sorribes , Victor Guallar , Alexis Molina

Graph Neural Networks (GNNs) face two fundamental challenges when scaled to deep architectures: oversmoothing, where node representations converge to indistinguishable vectors, and oversquashing, where information from distant nodes fails…

Machine Learning · Computer Science 2026-03-30 Mostafa Haghir Chehreghani

Message passing is the dominant paradigm in Graph Neural Networks (GNNs). The efficiency of message passing, however, can be limited by the topology of the graph. This happens when information is lost during propagation due to being…

Machine Learning · Computer Science 2024-11-05 Floriano Tori , Vincent Holst , Vincent Ginis

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

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

Message Passing Neural Networks (MPNNs) are widely used for learning on graphs, but their ability to process long-range information is limited by the phenomenon of oversquashing. This limitation has led some researchers to advocate Graph…

Machine Learning · Computer Science 2025-11-26 Yaaqov Mishayev , Yonatan Sverdlov , Tal Amir , Nadav Dym

Most graph neural networks (GNNs) are prone to the phenomenon of over-squashing in which node features become insensitive to information from distant nodes in the graph. Recent works have shown that the topology of the graph has the…

Machine Learning · Computer Science 2023-11-30 Julia Balla

Since the proposal of the graph neural network (GNN) by Gori et al. (2005) and Scarselli et al. (2008), one of the major problems in training GNNs was their struggle to propagate information between distant nodes in the graph. We propose a…

Machine Learning · Computer Science 2021-03-10 Uri Alon , Eran Yahav

Graph Neural Networks (GNNs) perform computations on graphs by routing the signal between graph regions using a graph shift operator or a message passing scheme. Often, the propagation of the signal leads to a loss of information, where the…

Machine Learning · Computer Science 2026-05-14 Eden Nagar , Ya-Wei Eileen Lin , Ron Levie

A common problem in Message-Passing Neural Networks is oversquashing -- the limited ability to facilitate effective information flow between distant nodes. Oversquashing is attributed to the exponential decay in information transmission as…

Machine Learning · Computer Science 2025-03-03 Alessio Gravina , Moshe Eliasof , Claudio Gallicchio , Davide Bacciu , Carola-Bibiane Schönlieb

Recent research in the field of graph neural network (GNN) has identified a critical issue known as "over-squashing," resulting from the bottleneck phenomenon in graph structures, which impedes the propagation of long-range information.…

Machine Learning · Computer Science 2024-07-23 Jeongwhan Choi , Sumin Park , Hyowon Wi , Sung-Bae Cho , Noseong Park

Deploying graph neural networks (GNNs) on whole-graph classification or regression tasks is known to be challenging: it often requires computing node features that are mindful of both local interactions in their neighbourhood and the global…

Machine Learning · Computer Science 2022-12-22 Andreea Deac , Marc Lackenby , Petar Veličković

Message passing neural networks iteratively generate node embeddings by aggregating information from neighboring nodes. With increasing depth, information from more distant nodes is included. However, node embeddings may be unable to…

Machine Learning · Computer Science 2024-03-29 Franka Bause , Samir Moustafa , Johannes Langguth , Wilfried N. Gansterer , Nils M. Kriege

Graph neural networks (GNNs) rely mainly on the message-passing paradigm to propagate node features and build interactions, and different graph learning problems require different ranges of node interactions. In this work, we explore the…

Machine Learning · Computer Science 2026-01-08 Fang Wu , Siyuan Li , Stan Z. Li

Graph Neural Networks (GNNs) excel on homophilous graphs but often fail under heterophily due to self-reinforcing and phase-inconsistent signals. We propose a \textbf{G}auge-\textbf{E}quivariant Graph Network with \textbf{S}elf-Interference…

Machine Learning · Computer Science 2026-05-20 Yoonhyuk Choi , Jiho Choi , Jiwoo Kang

Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input. However, they operate on a fixed input graph structure, ignoring potential noise and missing information. Furthermore, their…

Machine Learning · Computer Science 2024-03-27 Chendi Qian , Andrei Manolache , Kareem Ahmed , Zhe Zeng , Guy Van den Broeck , Mathias Niepert , Christopher Morris

Over-squashing is a challenge in training graph neural networks for tasks involving long-range dependencies. In such tasks, a GNN's receptive field should be large enough to enable communication between distant nodes. However, gathering…

Machine Learning · Computer Science 2025-08-29 Tuğrul Hasan Karabulut , İnci M. Baytaş

Graph Neural Networks (GNNs) are popular deep learning models designed to process graph-structured data through recursive neighborhood aggregations in the message passing process. When applied to semi-supervised node classification, the…

Machine Learning · Computer Science 2025-01-13 Kevin Mancini , Islem Rekik

In spite of the plethora of success stories with graph neural networks (GNNs) on modelling graph-structured data, they are notoriously vulnerable to over-squashing, whereby tasks necessitate the mixing of information between distance pairs…

Machine Learning · Computer Science 2025-05-20 JJ Wilson , Maya Bechler-Speicher , Petar Veličković

Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification. Recent researches show that graph neural networks are vulnerable to adversarial attacks, which…

Machine Learning · Computer Science 2019-10-01 Yao Ma , Suhang Wang , Tyler Derr , Lingfei Wu , Jiliang Tang