paper-with-me

홈 › Papers

On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems

2025-04-11 · AAAI 2025 4 · Alessio Gravina, Moshe Eliasof, Claudio Gallicchio, Davide Bacciu, Carola-Bibiane Schönlieb

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 node distances increase. This paper introduces a novel perspective to address oversquashing, leveraging dynamical systems properties of global and local non-dissipativity, that enable the maintenance of a constant information flow rate. We present SWAN, a uniquely parameterized GNN model with antisymmetry both in space and weight domains, as a means to obtain non-dissipativity. Our theoretical analysis asserts that by implementing these properties, SWAN offers an enhanced ability to transmit information over extended distances. Empirical evaluations on synthetic and real-world benchmarks that emphasize long-range interactions validate the theoretical understanding of SWAN, and its ability to mitigate oversquashing.

📄 PDF Abstract BibTeX

Code (1)

gravins/SWAN pytorch

Methods 이 논문이 사용한 방법론

Exponential Decay Exponential Decay is a learning rate schedule where we decay the learning rate with more iterations using an exponential function: $$ \text{lr} =…

Similar Papers 제목 키워드 기반

Understanding Oversquashing in GNNs through the Lens of Effective Resistance

2023-02-14 · Mitchell Black, Zhengchao Wan, Amir Nayyeri, Yusu Wang

Message passing graph neural networks (GNNs) are a popular learning architectures for graph-structured data. However, one problem GNNs experience is oversquashing, where a GNN has difficulty sending information between d…

Oversquashing in GNNs through the lens of information contraction and graph expansion

2022-08-06 · Pradeep Kr. Banerjee, Kedar Karhadkar, Yu Guang Wang, Uri Alon 외

The quality of signal propagation in message-passing graph neural networks (GNNs) strongly influences their expressivity as has been observed in recent works. In particular, for prediction tasks relying on long-range int…

graph construction

Understanding Virtual Nodes: Oversmoothing, Oversquashing, and Node Heterogeneity

2024-05-22 · Joshua Southern, Francesco Di Giovanni, Michael Bronstein, Johannes F. Lutzeyer

Message passing neural networks (MPNNs) have been shown to have limitations in terms of expressivity and modeling long-range interactions. Augmenting MPNNs with a virtual node (VN) removes the locality constraint of the …

Sensitivity

Oversmoothing, "Oversquashing", Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning

2025-05-21 · Adrian Arnaiz-Rodriguez, Federico Errica

After a renaissance phase in which researchers revisited the message-passing paradigm through the lens of deep learning, the graph machine learning community shifted its attention towards a deeper and practical understan…

Graph Unitary Message Passing

2024-03-17 · Haiquan Qiu, Yatao Bian, Quanming Yao

Message passing mechanism contributes to the success of GNNs in various applications, but also brings the oversquashing problem. Recent works combat oversquashing by improving the graph spectrums with rewiring techniques…

Graph Learning