paper-with-me

Papers

Message-Passing GNNs Fail to Approximate Sparse Triangular Factorizations

2025-02-03 · Vladislav Trifonov, Ekaterina Muravleva, Ivan Oseledets

Graph Neural Networks (GNNs) have been proposed as a tool for learning sparse matrix preconditioners, which are key components in accelerating linear solvers. This position paper argues that message-passing GNNs are fundamentally incapable of approximating sparse triangular factorizations. We demonstrate that message-passing GNNs fundamentally fail to approximate sparse triangular factorizations for classes of matrices for which high-quality preconditioners exist but require non-local dependencies. To illustrate this, we construct a set of baselines using both synthetic matrices and real-world examples from the SuiteSparse collection. Across a range of GNN architectures, including Graph Attention Networks and Graph Transformers, we observe severe performance degradation compared to exact or K-optimal factorizations, with cosine similarity dropping below $0.6$ in key cases. Our theoretical and empirical results suggest that architectural innovations beyond message-passing are necessary for applying GNNs to scientific computing tasks such as matrix factorization. Experiments demonstrate that overcoming non-locality alone is insufficient. Tailored architectures are necessary to capture the required dependencies since even a completely non-local Graph Transformer fails to match the proposed baselines.

📄 PDF Abstract BibTeX arXiv:2502.01397

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Attention

Methods 이 논문이 사용한 방법론

LapEigen 설명 없음
Laplacian PE Laplacian eigenvectors represent a natural generalization of the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음
Graph Transformer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations

2025-05-29 · Juwei Yue, Haikuo Li, Jiawei Sheng, XiaoDong Li 외

Graph neural networks (GNNs) leverage message passing mechanisms to learn the topological features of graph data. Traditional GNNs learns node features in a spatial domain unrelated to the topology, which can hardly ensu…

Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation

2026-05-24 · Zichao Yue, Zhiru Zhang arxiv

Pre-propagation graph neural networks (PPGNNs) decouple node feature propagation from transformation: graph diffusion is performed once as preprocessing, and training reduces to dense per-node transformations. This desig…

A non-asymptotic distributional theory of approximate message passing for sparse and robust regression

2024-01-08 · Gen Li, Yuting Wei

Characterizing the distribution of high-dimensional statistical estimators is a challenging task, due to the breakdown of classical asymptotic theory in high dimension. This paper makes progress towards this by developin…

regression

What Expressivity Theory Misses: Message Passing Complexity for GNNs

2025-09-01 · Niklas Kemper, Tom Wollschläger, Stephan Günnemann arxiv

Expressivity theory, characterizing which graphs a GNN can distinguish, has become the predominant framework for analyzing GNNs, with new models striving for higher expressivity. However, we argue that this focus is misg…

Sparse Multinomial Logistic Regression via Approximate Message Passing

2015-09-15 · Evan Byrne, Philip Schniter

For the problem of multi-class linear classification and feature selection, we propose approximate message passing approaches to sparse multinomial logistic regression (MLR). First, we propose two algorithms based on the…

feature selectionGeneral Classificationregression