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.

168,657 papers · 148 categories

Trend · papers per month

2675348001,067 · Jun 202019922001200920172026
48 results for Graph Neural Simulators

Hybrid model combines neural networks and fluid dynamics for efficient, generalized simulations.

problem Inefficient and poor generalization of deep learning approximations of fluid dynamics.
method Combines graph neural networks with a differentiable PDE solver inside a neural network.
result Hybrid model generalizes well to new scenarios and outperforms both neural network and traditional methods.

Improved GNN simulation of WL test with exponentially lower complexity.

problem Improving the complexity of simulating the Weisfeiler-Lehman test with GNNs.
method Exponentially lower complexity simulation of WL test using GNNs with polylogarithmic parameters and O(log n) bits feature vectors.
result Near-optimal construction with logarithmic lower bounds for feature vector length and neural network size.

Proposes a model combining graph networks and variational Bayes for graph data.

problem Probabilistic modeling of graph structured data.
method Combines graph networks and variational Bayes for probabilistic modeling of graph data.
result Demonstrates effectiveness on wind farm monitoring and Gaussian Process data.

New method extracts cosmological information from dark matter halo catalogues using graph neural networks.

problem Quantifying cosmological information from large-scale structure data.
method Implicit likelihood approach with Information Maximising Neural Networks (IMNNs) on graph representations of dark matter halo catalogues.
result Graph neural network summaries can extract information from noisy catalogues and improve parameter constraints.

Graph neural controlled differential equations learn graph dynamics from vertex observations.

problem Predicting future states of dynamical systems on graphs with limited vertex data.
method Incorporates graph topology information into NCDE to predict graph dynamics.
result Informed NCDE requires fewer parameters and lower MAE compared to previous methods.

Graph Neural Simulators improve data efficiency for PDE surrogates.

problem Lack of data efficiency in neural operators for PDE systems.
method Graph Neural Simulators (GNS) leverage message-passing and numerical time-stepping to learn PDE dynamics efficiently.
result GNS achieves less than 1% relative L2 error using only 3% of available trajectories.

This work benchmarks neural embeddings for link prediction in evolving knowledge graphs.

problem Evaluating the robustness of neural embeddings in changing knowledge graphs.
method Proposes an open-source evaluation pipeline using relation-centric connectivity measures.
result Demonstrates the importance of simulating embedding accuracy for frequently updated knowledge graphs.

A new method boosts graph neural networks by preventing over-smoothing and over-squashing.

problem Graph Neural Networks struggle with long-range signals and over-smoothing/over-squashing.
method Proposes PowerEmbed, a layer-wise normalization technique inspired by spectral graph embedding.
result PowerEmbed prevents over-smoothing and avoids over-squashing, improving performance on heterophilous graphs.

Graph convolutional networks fail to use eigenvectors beyond the first, unlike spectral embedding.

problem Understanding when graph convolutional networks fail compared to spectral embedding.
method Presented a simple generative model to illustrate failure.
result Graph convolutional networks fail to use eigenvectors beyond the first in certain graphs.

Graph neural networks benefit from a new initialization method that improves node learning.

problem Poor initialization in GNNs leads to slower convergence and increased training instability.
method Integrates a statistically grounded one-hot graph encoder embedding (GEE) into standard GNNs.
result GG framework provides consistent and substantial performance gains in node classification.

BetaExplainer improves GNN interpretability by masking unimportant edges.

problem Interpreting GNNs' predictions is difficult due to black-box behavior and lack of uncertainty quantification.
method BetaExplainer uses a sparsity-inducing prior to mask unimportant edges during training.
result BetaExplainer provides uncertainty in edge importance and improves predictive accuracy on challenging datasets.

CopulaGNN integrates graph representational and correlational roles for better node-level predictions.

problem Graphs encode diverse roles in node-level prediction tasks, but GNNs struggle with correlational information.
method Copula theory to describe multivariate dependence, integrating representational and correlational graph information.
result CopulaGNN improves GNN performance on regression tasks by leveraging both types of graph information.

TGNN4I model forecasts irregularly observed graph data using ODEs.

problem Forecasting graph-structured data with irregular time steps and partial observations.
method Introduces a time-continuous latent state in each node using ODEs and GRUs, integrating graph neural network layers.
result Validated usefulness of graph structure and time-continuous dynamics in irregular observation settings.

BeGIN benchmarks GNNs for instance-dependent label noise in graphs.

problem Instance-dependent label noise in graph data.
method BeGIN introduces a benchmark with various noise types and evaluates noise-handling strategies across GNN architectures.
result Challenges of instance-dependent noise, especially LLM-based corruption, and the importance of node-specific parameterization.

A new graph neural network framework captures long-range interactions efficiently.

problem Efficiently modeling long-range interactions in graph neural networks for PDEs.
method Proposes a multi-level graph neural network framework using multipole methods.
result Captures interaction at all ranges with only linear complexity, learning discretization-invariant solution operators.

A new graph generator uses heat diffusion on graph Laplacians to create new graph structures.

problem Creating realistic and diverse graph structures for various applications.
method Adapting the Generator Matching paradigm to graph data, using graph Laplacian and heat kernel for diffusion.
result The method effectively generates graphs with structural properties of real and synthetic graphs.

MaGNet integrates local and global graph information for interpretable results.

problem Lack of interpretability and inability to learn varying-order representations in GNNs.
method Model-agnostic Graph Neural Network (MaGNet) framework integrating estimation and interpretation models.
result MaGNet effectively integrates information of various orders and provides meaningful, interpretable results.

Graph neural networks improve solving linear optimization problems.

problem Improving the efficiency of solving linear optimization problems.
method Using graph neural networks to simulate standard interior-point methods for linear optimization problems.
result Graph neural networks can solve linear optimization problems close to optimality, often outperforming conventional solvers.

BAM model learns graph structure from data with robustness across linear and non-linear dependencies.

problem Detecting dependencies in datasets for graph structure learning.
method Proposes BAM, a neural network model using structural equation models and Chebyshev polynomials for training, with bilinear attention mechanism.
result Demonstrates robust generalizability and superior performance in graph estimation.

kth-order invariant graph networks are as powerful as kth-order WL in distinguishing graphs.

problem Measuring the expressive power of graph neural network formalisms.
method Considered kth-order invariant graph networks (k-IGNs) and compared their expressive power to kth-order WL.
result k-IGNs and k-WL are equally powerful in distinguishing graphs.

GemNet improves molecular predictions by overcoming graph neural network limitations.

problem Graph neural networks struggle with distinguishing certain types of molecular graphs.
method Discretized geometric message passing neural network (GemNet) with spherical representations.
result GemNet outperforms previous models on molecular datasets by 34-20%.

engGNN combines external and generated graphs to improve disease classification and biomarker discovery.

problem Challenges in integrating omics data due to high dimensionality and small sample sizes.
method Dual-graph framework that integrates external biological networks with data-driven generated graphs.
result engGNN outperforms state-of-the-art methods in disease classification and biomarker discovery.

New method calibrates ABMs using graph neural networks for microdata.

problem Calibrating ABMs to granular microdata with high-dimensional learning tasks.
method Temporal graph neural networks for learning parameter posteriors.
result Graph neural networks offer inductive biases for Bayesian inference with ABM microstates.

Paper compares GCNs and MPNNs, finding GCNs are one step ahead of WL algorithm.

problem Comparing graph convolutional networks (GCNs) and message-passing neural networks (MPNNs).
method Casts GCNs and MPNNs as MPNNs, studies distinguishing power of different architectures.
result GCNs are one step ahead of the Weisfeiler-Lehman (WL) algorithm in distinguishing power.

This study uses deep learning to improve the accuracy of raw data denoising in ProtoDUNE experiments.

problem Improving the accuracy of raw data denoising in ProtoDUNE experiments.
method Investigates two graph neural network architectures to enhance the receptive field of convolutional neural networks for raw data denoising.
result Graph neural network architectures outperform traditional algorithms in denoising raw ProtoDUNE data.

Neural Architecture Search (NAS) enabled the discovery of state-of-the-art architectures in many domains. However, the success of NAS depends on the definition of the search space. Current search spaces are defined as a static sequence of decisions and a set of available actions for each decision. Each possible sequenc…

2018-12-27abs ↗pdf ↗

New method infers causal factors from large-scale data without full graph reconstruction.

problem Inferring causal variables from large-scale systems without full causal graph reconstruction.
method Supervised learning on simulated data using a neural network and subsampled-ensemble inference.
result Efficiently identifies causal relationships in large-scale gene regulatory networks.

We introduce JAX MD, a software package for performing differentiable physics simulations with a focus on molecular dynamics. JAX MD includes a number of physics simulation environments, as well as interaction potentials and neural networks that can be integrated into these environments without writing any additional c…

2019-12-09abs ↗pdf ↗