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.

169,181 papers · 148 categories

Trend · papers per month

135270404539 · Jun 202019922001200920182026
48 results for subgraph sampling

GNNS uses graph neural networks to efficiently estimate subgraph frequency distributions.

problem Efficiently calculating subgraph frequency distributions in large networks.
method Graph Neural Networks (GNNS) for sampling and estimating subgraph frequencies.
result GNNS achieves comparable accuracy with a significant speedup of three orders of magnitude.

Unified framework for subgraph-enhanced GNNs, improving prediction accuracy and reducing computation time.

problem Limited understanding of subgraph-enhanced GNNs and their relation to the Weisfeiler-Leman hierarchy.
method Theoretical framework, theoretical expressivity results, and data-driven subgraph sampling methods.
result Data-driven subgraph-enhanced GNNs outperform non-data-driven methods in predictive performance.

SubGNN tackles subgraph prediction challenges in graphs.

problem Subgraphs in graphs are challenging to predict due to their internal topology and external connectivity.
method SubGNN introduces a novel subgraph routing mechanism to learn disentangled subgraph representations.
result SubGNN achieves considerable performance gains on subgraph classification tasks, outperforming strong baseline methods.

DSL learns discriminative subgraphs from graphs for robust prediction.

problem Learning discriminative subgraphs from graph data for robust prediction.
method Discriminative Subgraph Learning (DSL) framework that enforces sparsity, connectivity, and high discriminative power.
result DSL improves prediction accuracy by up to 16% compared to baselines.

Ripple Walk Training tackles graph neural network training issues for large and deep graphs.

problem Neighbors explosion, node dependence, and oversmoothing in large and deep GNNs.
method Subgraph-based training framework with Ripple Walk Sampler for high-quality subgraph sampling.
result RWT improves training efficiency and reduces space complexity for deep and large GNNs.

Detecting edge correlation between two graphs sharpens a threshold based on densest subgraph.

problem Detecting edge correlation between two Erdős-Rényi graphs.
method Formulated as a hypothesis testing problem, connecting to densest subgraph detection.
result Sharp information-theoretic threshold established for edge correlation detection.

Estimates the number of connected components in a graph from a sampled subgraph.

problem Inferring the number of connected components in a larger graph from a sampled subgraph.
method A highly redundant and large-dimensional representation of the subgraph using counts of network motifs, leading to a novel estimator for the number of connected components.
result Improves upon competing algorithms for graphs with spectral gaps bounded away from zero.

VISTA learns causal structures by integrating local subgraphs, improving accuracy and efficiency.

problem Efficiently learning causal structures from high-dimensional observational data.
method VISTA decomposes the global causal structure learning problem into local subgraphs based on Markov Blankets, integrating them via a weighted voting mechanism.
result VISTA achieves notable improvements in accuracy and efficiency over existing methods.

The study proves sampling-based GNNs can approximate training on full graphs with small subgraphs.

problem Training Graph Neural Networks (GNNs) on large graphs is computationally expensive.
method Theoretical framework using graph local limits to prove approximation of GNN training on small samples.
result Parameters learned from sampling-based GNNs on small subgraphs are close to those on full graphs.

Method learns big Gaussian Bayesian networks by clustering, estimating, and fusing subgraphs.

problem Learning structure of large Bayesian networks with many nodes and few samples.
method Partition-estimation-fusion (PEF) framework: hierarchical clustering, subgraph learning, edge fusion.
result PEF method improves structure learning accuracy by 20% or more, with up to two orders-of-magnitude faster running time.

As a model problem for clustering, we consider the densest k-disjoint-clique problem of partitioning a weighted complete graph into k disjoint subgraphs such that the sum of the densities of these subgraphs is maximized. We establish that such subgraphs can be recovered from the solution of a particular semidefinite re…

2016-03-16abs ↗pdf ↗

Paper solves feature selection for two distributions without parametric assumptions.

problem Feature selection for two different probability distributions.
method Sparsest k-subgraph problem formulation for nonparametric feature selection.
result Consistent estimator of features under mild conditions.

NeuroMatch efficiently matches subgraphs in large graphs using neural networks.

problem Determining the presence and location of a query graph in a large target graph.
method NeuroMatch decomposes graphs into subgraphs, embeds them using graph neural networks, and matches them directly in the embedding space.
result NeuroMatch is 100x faster and 18% more accurate than existing methods.

A new algorithm identifies interpretable network representations via subgraph count statistics.

problem Interpreting network-valued data samples.
method Principal Component Analysis for Networks (PCAN) and its fast sampling-based version (sPCAN).
result The PCAN and sPCAN methods provide informative and discriminatory features for network samples.

We propose graph kernels based on subgraph matchings, i.e. structure-preserving bijections between subgraphs. While recently proposed kernels based on common subgraphs (Wale et al., 2008; Shervashidze et al., 2009) in general can not be applied to attributed graphs, our approach allows to rate mappings of subgraphs by …

2012-06-27abs ↗pdf ↗

Subg-Con learns graph representations from subgraphs, improving scalability and efficiency.

problem Scalability issues and weak supervision in graph representation learning.
method Subg-Con uses subgraphs sampled from the original graph to define a contrastive loss, learning node representations without complete graph data.
result Subg-Con outperforms existing methods in scalability, efficiency, and weak supervision requirements.

Efficiently learns subgraph patterns and nonlinear models for graph inputs.

problem Learning relevant subgraph patterns and nonlinear models from large combinatorial inputs.
method Jointly learns subgraph patterns and nonlinear models using gradient boosting.
result Can learn nonlinear models through standard gradient boosting.

Proposes GIB for recognizing informative subgraphs in graphs.

problem Recognizing a subgraph that is maximally informative yet compressive.
method Graph Information Bottleneck (GIB) framework, mutual information estimator, bi-level optimization, connectivity loss.
result IB-subgraph improves graph classification, interpretation, and denoising.

Faster algorithm for generalized mean densest subgraph problem.

problem Finding subgraphs with highest average pp-th-power degree.
method GENPEEL++ algorithm, which yields (2(p+1))1/p(2(p+1))^{1/p}-approximation for p[1,+)p \in [1, +\infty) with time complexity O(m(logn))O(m(\log n)).
result GENPEEL++ algorithm provides faster and more efficient solution for generalized mean densest subgraph problem.

Researchers find a finite rigid subgraph in pants graphs of surfaces.

problem Identifying a finite rigid subgraph in pants graphs of surfaces.
method Identifying a finite rigid subgraph Xg,nX_{g,n} of pants graph P(Sg,n)\mathcal P (S_{g,n}).
result Any simplicial embedding of Xg,nX_{g,n} into any pants graph P(Sg,n)\mathcal P (S_{g',n'}) is induced by an embedding Sg,noSg,nS_{g,n} o S_{g',n'}.

Estimates eigenvalues of poly-Laplace operator on lattice subgraphs.

problem Estimating eigenvalues of poly-Laplace operator on subgraphs of lattice graphs.
method Introduced discrete poly-Laplace operator, derived upper and lower bounds for eigenvalues.
result Poly-Laplace eigenvalues are at least squares of lower-order poly-Laplace eigenvalues.

Mining discriminative features for graph data has attracted much attention in recent years due to its important role in constructing graph classifiers, generating graph indices, etc. Most measurement of interestingness of discriminative subgraph features are defined on certain graphs, where the structure of graph objec…

2013-01-28abs ↗pdf ↗

SubSearch detects graph outliers and estimates SBM parameters robustly.

problem Real-world graphs often deviate from ideal SBM assumptions.
method Subgraph search to find subgraphs that align with SBM assumptions.
result SubSearch accurately estimates SBM parameters and detects outliers.

We present a supervised-learning algorithm from graph data (a set of graphs) for arbitrary twice-differentiable loss functions and sparse linear models over all possible subgraph features. To date, it has been shown that under all possible subgraph features, several types of sparse learning, such as Adaboost, LPBoost, …

2014-03-20abs ↗pdf ↗

Upper bounds for Steklov eigenvalues in subgraphs of polynomial growth Cayley graphs.

problem Finding upper bounds for Steklov eigenvalues in subgraphs of polynomial growth Cayley graphs.
method Discretizing a bounded domain and using comparison theorems.
result The $k^{\mbox{th}}$ eigenvalue tends to 00 proportionally to 1/B1d11/|B|^{\frac{1}{d-1}}.

GMT improves interpretability of XGNNs by approximating SubMT.

problem Limited understanding of existing interpretable subgraph learning methods.
method Formulated subgraph multilinear extension (SubMT) and designed GMT architecture.
result GMT outperforms state-of-the-art in both interpretability and generalizability.

SELO model predicts link signs better than SDGNN using subgraph encoding and linear optimization.

problem Inferring the sign of links in signed networks with limited sign data.
method Subgraph Encoding via Linear Optimization (SELO) approach to learn edge embeddings.
result SELO model outperforms state-of-the-art methods on multiple real-world signed networks.

Neural network for subgraph similarity computation with pruning.

problem Computing subgraph similarity between a target and query graph.
method Convert pruning to node relabeling, relax to differentiable problem, design neural network for SED computation.
result Establishes new state-of-the-art results across multiple benchmark datasets.

PSimGNN partitions graphs into subgraphs for efficient graph similarity computation.

problem Efficiently compute graph similarity scores for large graphs.
method Graph partitioning followed by subgraph-level and node-level comparisons using a graph neural network.
result PSimGNN outperforms state-of-the-art methods in graph similarity computation tasks.

R-GPM enables efficient graph pattern mining through user-defined relations.

problem Efficient graph pattern mining through user-defined relations.
method Parallel computing framework with MCMC sampling algorithm and optimizations.
result Efficient estimators for graph pattern statistics with up to 3-orders-of-magnitude computational cost reduction.