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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

12 results for “k-hop”

k-hop Graph Neural Networksstat.ML

k-hop GNNs improve GNNs' ability to identify graph properties.

problem GNNs' limitations in identifying fundamental graph properties.

method Proposes k-hop GNNs that aggregate information from a node's k-hop neighborhood.

result k-hop GNNs can identify fundamental graph properties.

Graph Neural Networks k-hop Fundamental Graph Properties Node Classification Graph Classification

2019-07-13abs ↗pdf ↗

A Clifford Algebraic Approach to E(n)-Equivariant High-order Graph Neural Networkscs.LG

Novel CG-EGNNs learn equivariant functions from Clifford algebras.

problem Lack of equivariance in high-order graph neural networks.

method Integrates high-order local structures with Clifford algebras for equivariant learning.

result CG-EGNNs outperform previous methods on various benchmarks.

Clifford algebra equivariant graph neural networks high-order message passing geometric deep learning equivariance

2024-10-07abs ↗pdf ↗

Attentive Walk-Aggregating Graph Neural Networkscs.LG

AWARE improves graph prediction by aggregating walks with attention schemes.

problem Improving graph prediction accuracy using walk aggregation.

method Integrates attention schemes into walk-aggregating GNNs.

result AWARE outperforms existing methods in graph-level prediction tasks.

Graph Neural Networks Walk Aggregation Attention Mechanism Graph Prediction Molecular Property Prediction

2021-10-06abs ↗pdf ↗

Are GNNs doomed by the topology of their input graph?stat.ML

GNNs may be limited by graph topology, affecting their learning outcomes.

problem Understanding how graph topology influences GNN behavior and performance.

method Investigating the interaction between local topological features and GNN message-passing schemes.

result Locally similar neighborhoods can lead to consistent node representations, affecting GNN performance.

Graph Neural Networks Graph Topology Message-Passing Oversmoothing Local Similarity

2025-02-25abs ↗pdf ↗

Understanding over-squashing and bottlenecks on graphs via curvaturestat.ML

Graph rewiring method alleviates over-squashing in GNNs.

problem Over-squashing and bottlenecks in graph neural networks.

method Curvature-based graph rewiring method.

result Negatively curved edges cause over-squashing in GNNs.

Graph Neural Networks Over-squashing Bottlenecks Curvature Rewiring

2021-11-29abs ↗pdf ↗

Structure Aware Negative Sampling in Knowledge Graphscs.LG

SANS uses graph structure to find meaningful negatives for entity and relation embeddings.

problem Finding hard negatives for entity and relation embeddings in knowledge graphs.

method Structure Aware Negative Sampling (SANS) that selects negatives from a node's k-hop neighborhood.

result SANS finds semantically meaningful negatives and is competitive with state-of-the-art approaches.

knowledge graph negative sampling contrastive learning graph structure entity embedding

2020-09-23abs ↗pdf ↗

Smoothing the Landscape: Causal Structure Learning via Diffusion Denoising Objectivescs.LG

DDCD uses diffusion models to learn causal structures from noisy data.

problem Scalability and stability issues in high-dimensional causal structure learning.

method Adaptive k-hop acyclicity constraint and denoising score matching objective of diffusion models.

result DDCD achieves competitive performance on synthetic and real-world data.

causal discovery diffusion models denoising graphical models scalability

2026-04-02abs ↗pdf ↗

Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheavescs.LG

PolyNSD improves Neural Sheaf Diffusion with polynomial operators and spectral rescaling.

problem Limitations of common Neural Sheaf Diffusion implementations, including scalability and stability issues.

method Introduces Polynomial Neural Sheaf Diffusion (PolyNSD) with a degree-K polynomial propagation operator and spectral rescaling.

result PolyNSD achieves state-of-the-art results on both homophilic and heterophilic benchmarks with reduced runtime and memory requirements.

Neural Sheaf Diffusion Polynomial Operators Spectral Rescaling Stability Heterophily

2025-11-28abs ↗pdf ↗

Position: Don't be Afraid of Over-Smoothing And Over-Squashingstat.ML

Advocates against over-smoothing and over-squashing in GNNs, suggesting they are less critical than previously thought.

problem Over-smoothing and over-squashing in Graph Neural Networks (GNNs).

method Challenged the prevailing focus on these phenomena, proposing that performance decreases are due to uninformative receptive fields and localised information distribution.

result Performance decreases are mostly uncorrelated with over-smoothing and over-squashing, and optimal model depths remain small.

Graph Neural Networks Over-smoothing Over-squashing Receptive Fields Localised Information

2026-01-12abs ↗pdf ↗

Class-Attentive Diffusion Network for Semi-Supervised Classificationcs.LG

AdaCAD improves semi-supervised classification by focusing on intra-class nodes.

problem Improving semi-supervised classification by addressing inter-class connections in graphs.

method AdaCAD uses a class-attentive diffusion process to adaptively aggregate nodes based on their class similarity.

result AdaCAD significantly outperforms state-of-the-art methods in semi-supervised classification.

graph neural networks semi-supervised classification class-attentive diffusion inter-class connections node aggregation

2020-06-18abs ↗pdf ↗

PushNet: Efficient and Adaptive Neural Message Passingcs.LG

PushNet efficiently and adaptively pushes messages in neural networks, improving performance.

problem Inefficient and inflexible synchronous message passing in neural networks.

method Asynchronous message passing with adaptive receptive fields and multiple scale correlations.

result PushNet outperforms competitors in semi-supervised node classification on multiple datasets.

neural networks message passing graph representation asynchronous adaptive receptive field

2020-03-04abs ↗pdf ↗

DAGCN: Dual Attention Graph Convolutional Networkscs.LG

DAGCN improves graph classification by learning neighbor importance and pooling.

problem Loss of early-stage information and loss of node characteristics in GCNs.

method Dual attention graph convolution and self-attention pooling.

result DAGCN outperforms state-of-the-art methods in graph classification.

graph convolutional networks attention mechanisms graph classification end-to-end training neighborhood aggregation

2019-04-04abs ↗pdf ↗