On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “oversquashing”

Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passingcs.LG

We analyze oversquashing in topological message-passing using relational structures.

problem Oversquashing in topological message-passing remains understudied.

method A unifying axiomatic framework that bridges graph and topological message-passing.

result Potential to advance topological deep learning.

topological deep learning oversquashing relational structures simplicial networks message-passing

2025-06-06abs ↗pdf ↗

FoSR: First-order spectral rewiring for addressing oversquashing in GNNscs.LG

FoSR adds edges to graphs to prevent oversquashing and oversmoothing in GNNs.

problem Oversquashing and oversmoothing in graph neural networks (GNNs).

method First-order spectral rewiring to add edges based on spectral expansion, combined with a relational architecture.

result Our algorithm outperforms existing graph rewiring methods in graph classification tasks.

graph neural networks oversquashing oversmoothing spectral expansion edge rewiring

2022-10-21abs ↗pdf ↗

Expander Graph Propagationcs.LG

EGP uses expander graphs to improve GNN performance.

problem Challenges in deploying GNNs on graph tasks, including bottlenecks and oversquashing.

method Proposes EGP model based on expander graph propagation.

result EGP addresses challenges without bottlenecks or oversquashing, with linear complexity.

graph neural networks expander graphs message passing oversquashing negative curvature

2022-10-06abs ↗pdf ↗

From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyondcs.LG

Graph neural networks are explained through heat diffusion analogy.

problem Limitations of graph neural networks (oversmoothing, oversquashing).

method Analogizing message passing in GNNs to heat dynamics.

result Fundamental understanding of GNNs and improved model design.

graph neural networks heat diffusion message passing continuous dynamics oversmoothing

2023-10-16abs ↗pdf ↗

Equivariant Matrix Function Neural Networksstat.ML

MFNs parameterize non-local interactions through matrix equivariant functions, improving graph neural network performance.

problem Challenges in modeling non-local interactions in graphs, such as oversmoothing and oversquashing.

method Matrix Function Neural Networks (MFNs) using resolvent expansions for non-local interactions.

result Achieves state-of-the-art performance in graph benchmarks and captures intricate non-local interactions.

Graph Neural Networks Matrix Functions Non-local Interactions Spectral GNNs Resolvent Expansions

2023-10-16abs ↗pdf ↗

SCNode: Spatial and Contextual Coordinates for Graph Representation Learningcs.LG

SCNode improves node embeddings for GNNs in both homophilic and heterophilic graphs.

problem Challenges in node representation quality and generalization in GNNs, especially in heterophilic graphs.

method SCNode integrates spatial and contextual information to create more discriminative and structurally aware node embeddings.

result SCNode achieves superior performance over conventional GNN models on benchmark datasets.

Graph Neural Networks Node Embedding Spatial-Contextual Homophily Heterophily

2024-10-03abs ↗pdf ↗

Limits of message passing for node classification: How class-bottlenecks restrict signal-to-noise ratiocs.LG

MPNNs struggle with class-bottlenecks and heterophily, leading to performance limitations.

problem Performance limitations of MPNNs under heterophily and structural bottlenecks.

method A statistical framework decomposing model performance into SNR components and proving bounds on sensitivity.

result Optimal graph structures for maximizing higher-order homophily are disjoint unions of single-class and two-class-bipartite clusters.

Message Passing Neural Networks Node Classification Heterophily Structural Bottlenecks Signal-to-Noise Ratio

2025-08-25abs ↗pdf ↗