Research
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

2745498231,097 · Jun 202019922001200920172026
48 results for Graph Neural Networks (GNNs)

This thesis explores GNNs, categorizing them into local and global approaches.

problem Understanding the convergence of global GNNs and connecting local and global approaches.
method Categorization of GNNs into local and global, study of Invariant Graph Networks, connecting local and global approaches, and using local MPNN for graph coarsening.
result Established a connection between local and global GNN approaches.

Graph neural networks can be adapted to new graphs with a limit object called graphon NNs.

problem Transferability of graph neural networks across different graphs.
method Introduced graphon NNs as limit objects of GNNs and proved a bound on the difference between GNN and graphon-NN outputs.
result The bound on the difference between GNN and graphon-NN outputs vanishes with growing number of nodes if the graph convolutional filters are bandlimited.

SHAKE-GNN scales GNNs for large graphs with multi-scale representations.

problem Scaling Graph Neural Networks (GNNs) to large graphs.
method SHAKE-GNN uses a hierarchy of Kirchhoff Forests for stochastic multi-resolution graph decompositions.
result SHAKE-GNN achieves competitive performance on large-scale graph classification benchmarks.

Graph neural networks leverage graph filters to learn from network data.

problem Learning from network data with graph structure.
method Characterize graph neural networks using graph signal processing and graph convolutional filters.
result Graph neural networks have permutation equivariance and stability to topology changes.

LC-GNN improves GNNs for node classification by incorporating label consistency.

problem Limited performance of GNNs due to label consistency assumption not always holding.
method LC-GNN uses node pairs with the same label but unconnected to expand GNN's receptive field.
result LC-GNN outperforms traditional GNNs in semi-supervised node classification.

New research limits what GNNs can compute and generalizes their performance.

problem Limits of GNNs in computing graph properties and generalization bounds.
method Novel graph-theoretic formalism and data-dependent generalization bounds.
result Proves GNNs can't compute certain graph properties and provides tighter generalization bounds.

Alt-GNNs improve travel mode choice modeling by integrating graph neural networks with GEV models.

problem Capturing alternative dependence in discrete choice models with predefined, symmetric, and uniform dependence.
method Introducing Alternative Graph Neural Networks (Alt-GNNs) that embed alternative dependence within a unified framework.
result Alt-GNNs significantly improve predictive performance over benchmark models in travel mode choice datasets.

GNNs learn graph representations, with new theory on their power and limitations.

problem Understanding the capabilities and limitations of GNNs.
method Theoretical analysis of GNNs, focusing on approximation and learning properties.
result New insights into the representation, generalization, and extrapolation of GNNs.

Graph Neural Networks struggle on random graphs without node identifiers.

problem Graph Neural Networks' limitations on random graphs without node identifiers.
method Study of Graph Neural Networks and Structural Graph Neural Networks convergence on large random graphs.
result Structural Graph Neural Networks are more powerful and universal than Graph Neural Networks on random graphs.

GraphNorm accelerates GNN training by adapting InstanceNorm, improving convergence and generalization.

problem Improving convergence and generalization of Graph Neural Networks (GNNs).
method Adapting InstanceNorm to GNNs, proposing GraphNorm with a learnable shift.
result GNNs with GraphNorm converge faster and achieve better performance on benchmarks.

A new graph neural network (NBA-GNN) avoids revisiting nodes to improve accuracy.

problem Redundancy in graph neural network updates causes over-squashing and inaccurate recognition.
method Proposes non-backtracking graph neural networks (NBA-GNN) that update messages without revisiting nodes.
result The NBA-GNN alleviates over-squashing and improves performance on graph benchmarks.

The paper improves GNN generalization theory by considering graph manifolds.

problem Improper GNN generalization bounds ignoring graph structures.
method Taking a manifold perspective, the paper establishes GNN generalization theory.
result GNN generalization bounds decrease linearly with graph size and spectral continuity.

Sketch-GNN reduces GNN training time and memory usage to sublinear scales.

problem Training GNNs on large graphs is computationally expensive and memory-intensive.
method Develops a sketch-based algorithm that trains GNNs on compact sketches of graph adjacency and node embeddings.
result Training time and memory usage grow sublinearly with respect to graph size.

XGNN explains graph neural networks by generating graphs that maximize model predictions.

problem Lack of explainable models for graph neural networks.
method Train a graph generator to maximize model predictions, using reinforcement learning and graph rules.
result Generated graphs provide insights into how GNNs work and can guide model improvement.

Graph neural networks (GNNs) are powerful machine learning models for various graph learning tasks. Recently, the limitations of the expressive power of various GNN models have been revealed. For example, GNNs cannot distinguish some non-isomorphic graphs and they cannot learn efficient graph algorithms. In this paper,…

2020-02-08abs ↗pdf ↗

Eigen-GNN enhances GNNs by preserving graph structures.

problem Existing shallow GNNs fail to effectively preserve graph structures.
method Integrates eigenspace of graph structures into GNNs as a dimensionality reduction module.
result Eigen-GNN boosts GNNs' ability to preserve graph structures without increasing depth.

In recent years, graph neural networks (GNNs) have emerged as a powerful neural architecture to learn vector representations of nodes and graphs in a supervised, end-to-end fashion. Up to now, GNNs have only been evaluated empirically -- showing promising results. The following work investigates GNNs from a theoretical…

2018-10-04abs ↗pdf ↗

Develops GNNs for incomplete graphs, improving learning from missing node attributes.

problem Learning from incomplete graphs with missing node attributes.
method Introduces PaGNNs with novel partial aggregation functions for incomplete graph data.
result Demonstrates effectiveness and efficiency of PaGNNs on various datasets.

Neural GDEs improve graph prediction by blending discrete structures and differential equations.

problem Dynamic graph prediction challenges in irregularly sampled data.
method Continuous-depth graph neural networks (GNNs) with Neural GDEs.
result Neural GDEs enhance performance across various applications.

Propagation-regularization improves GNN performance by infusing extra graph information.

problem The effectiveness of graph Laplacian regularization in GNNs is questioned and improved upon.
method Introducing Propagation-regularization (P-reg) to enhance GNN performance.
result P-reg boosts GNN performance on various tasks across multiple datasets.

Unified framework sparsifies GNNs for faster inference on large graphs.

problem Space and computational bottlenecks in GNNs due to graph size and connectivity.
method Unified GNN sparsification (UGS) framework that prunes graph adjacency matrix and model weights.
result Graph lottery tickets (GLTs) can be trained in isolation to match full model performance.

Inspired by the immense success of deep learning, graph neural networks (GNNs) are widely used to learn powerful node representations and have demonstrated promising performance on different graph learning tasks. However, most real-world graphs often come with high-dimensional and sparse node features, rendering the le…

2019-08-19abs ↗pdf ↗

Pro-GNN defends graph neural networks from adversarial attacks by learning graph structure.

problem Vulnerability of GNNs to adversarial attacks on real-world graphs.
method Pro-GNN learns a structural graph and a robust GNN model jointly from perturbed graphs guided by intrinsic graph properties.
result Pro-GNN achieves significantly better performance than state-of-the-art defense methods, even on heavily perturbed graphs.

Graph neural networks improve topology control of power grids.

problem Grid congestion due to renewable energy and electrification.
method Investigated the effect of graph representation on GNN effectiveness for topology control.
result Heterogeneous graph representation outperforms homogeneous in topology control tasks.

Paper provides statistical guarantees for GNNs in link prediction.

problem Link prediction accuracy in graph neural networks.
method Proposes a linear GNN architecture (LG-GNN) and derives statistical guarantees.
result LG-GNN produces consistent estimators for edge probabilities and has better detection of high-probability edges.

Learning node embeddings that capture a node's position within the broader graph structure is crucial for many prediction tasks on graphs. However, existing Graph Neural Network (GNN) architectures have limited power in capturing the position/location of a given node with respect to all other nodes of the graph. Here w…

2019-06-11abs ↗pdf ↗

New method uses contrastively trained GNNs for more reliable graph model evaluation.

problem Need effective methods to evaluate Graph Generative Models.
method Use representations from contrastively trained Graph Neural Networks (GNNs) for evaluation.
result Contrastively trained GNNs provide more reliable evaluation metrics than traditional or GNN-based approaches.

SMP model preserves proximity and permutation in graph neural networks.

problem Challenges in graph mining, such as community and leader finding.
method Stochastic Message Passing (SMP) model that maintains proximity and permutation-equivariance.
result SMP model effectively preserves node proximities and permutation-equivariance.