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.

169,291 papers · 148 categories

Trend · papers per month

78155233310 · Jun 202019922001200920182026
48 results for dual graphs

Accelerated Gibbs sampling for Gaussian graphical models using dual factor graphs.

problem Improving convergence rate of Gibbs sampling for Gaussian graphical models.
method Dual normal factor graph approach to accelerate convergence.
result Universal convergence rate improvement in dual domain for all homogeneous models.

Random matrix models generalize to Group Field Theories (GFT) whose Feynman graphs are dual to gluings of higher dimensional simplices. It is generally assumed that GFT graphs are always dual to pseudo manifolds. In this paper we prove that already in dimension three (and in all higher dimensions), this is not true due…

2010-06-03abs ↗pdf ↗

We prove a mapping between dual and primal factor graph marginals for efficient estimation.

problem Efficient estimation of marginal densities in factor graphs.
method Local mappings derived from Fourier transforms of local factors, applied to Ising and Potts models.
result Marginal densities can be more accurately estimated in the dual domain.

In this note, I discuss in some detail the dual version of the ribbon graph decomposition of the moduli spaces of Riemann surfaces with boundary and marked points, which I introduced in math.AG/0402015, and used in math.QA/0412149 to construct open-closed topological conformal field theories. This dual version of the r…

2006-01-06abs ↗pdf ↗

Dual regularized graph Laplacian improves spectral clustering for community detection.

problem Detecting clusters in networks with improved spectral clustering methods.
method Proposes dual regularized graph Laplacian for three spectral clustering approaches.
result Theoretical analysis shows DRSC and DRSLIM yield stable consistent community detection.

MR-GNN predicts interactions between structured entities using multi-resolution and dual graph neural networks.

problem Predicting interactions between structured entities, especially considering features in substructures of different sizes and interactions between entities.
method MR-GNN uses a multi-resolution architecture and dual graph-state L-STMs to extract features from different neighborhoods and pairwise graphs, respectively.
result MR-GNN improves prediction accuracy compared to state-of-the-art methods.

FairDTD improves fairness in GNNs by distilling dual teacher knowledge, balancing utility and bias.

problem Bias in GNN predictions due to sensitive attributes.
method Dual-Teacher Distillation with a causal graph model, feature and structure teachers, and graph-level distillation.
result Achieves optimal fairness while preserving high model utility.

CADE learns dual node representations for better generalization.

problem Transductive graph embeddings cannot generalize to unseen nodes or across different graphs.
method CADE combines real-time neighborhoods with neighbor-attentioned representation, preserving known node memory.
result CADE outperforms state-of-the-art methods in generalization and context-awareness.

PDNAS optimizes GNN architectures for diverse datasets.

problem Inadequate adaptability and combinatorial search space in GNNs.
method Dual architecture search (micro- and macro-architectures) with gradient-based optimization.
result PDNAS finds deeper GNNs with better performance on diverse datasets.

The main results in this paper provide upper bounds of the second order Dehn functions for three-dimensional groups Nil and Sol. These upper bounds are obtained by using the Varopoulos transport argument on dual graphs. The first step is to start with reduced handlebody diagrams of the three-dimensional balls either im…

2010-10-17abs ↗pdf ↗

Local mappings relate dual and primal factor graphs for efficient marginal probability estimation.

problem Efficient estimation of marginal probabilities in statistical physics models.
method Local mappings based on Fourier transform of local factors, applied to Ising, Potts, and clock models.
result Local extrema of fixed points are at phase transition points, and the mapping facilitates efficient estimation.

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.

A new online learning algorithm for graph-structured sparsity.

problem Efficiently handling graph-structured sparsity constraints in online learning settings.
method Proposes extsc{GraphDA} algorithm that projects gradients and variables onto subspaces.
result Improves classification performance and captures graph-structured features effectively.

The study connects geodesic flows on Riemann surfaces to random walks on their dual graphs.

problem Understanding ergodicity of geodesic flows on infinite Riemann surfaces.
method Analyzing random walks on the dual graph of pants decompositions.
result Equivalence between ergodicity of geodesic flows and recurrence of random walks.

THGFM models dynamic relational systems with cross-type and temporal fusion.

problem Learning on temporal heterogeneous graphs with diverse node and relation types.
method Dual-Path Architecture with Shared-Space and Relational Type-Partitioned Temporal Attention.
result THGFM outperforms baseline models on academic graph benchmarks.

A formula calculates the Euler class of foliations using dual graphs.

problem Calculating the Euler class of foliations using cooriented branched surfaces.
method Using dual graphs of cooriented branched surfaces to define a simplicial 1-cycle representing the Poincaré dual of the Euler class.
result The formula generalizes previous results and classifies realizable homology classes.

Entire minimal graphs in Heisenberg space have negative Gauss curvature.

problem Characterizing entire minimal graphs in Heisenberg space.
method Defining holomorphic quadratic differentials and using them to describe entire graphs.
result Entire minimal graphs in Heisenberg space have negative Gauss curvature.

Dual-based algorithms optimize distributed convex problems over networks.

problem Optimizing distributed convex problems over network constraints.
method Dual formulation of primal problem, distributed algorithms achieving optimal rates.
result Achieves optimal rates similar to centralized algorithms with additional cost related to network spectral properties.

DanSmp predicts stock movement using a hybrid-relational MKG and dual attention networks.

problem Predicting stock price trends in volatile financial markets.
method Constructs a bi-typed MKG with hybrid-relations and uses DanSmp, a dual attention network, to learn momentum spillover signals.
result DanSmp improves stock prediction accuracy using the MKG.

The article studies embeddings of edge-colored graphs related to balanced 3- and 4-manifolds.

problem Investigating embeddings of edge-colored dual graphs of balanced 3- and 4-manifolds.
method Introducing the concept of balanced genus and proving lower bounds for the genus of 3- and 4-manifolds.
result Established lower bounds for the balanced genus of 3- and 4-manifolds, and conditions for homeomorphism to spheres.

Method uses TV minimization for semi-supervised learning on network data.

problem Semi-supervised learning from partially-labeled network data.
method Graph signal recovery interpretation, total variation minimization, primal-dual method for non-smooth convex optimization.
result TV minimization recovers clusters in the empirical graph of the data under certain network conditions.

Optimizes wireless network resource management with state-augmented policies.

problem Optimizing network-wide utility with user performance constraints.
method State-augmented parameterization of RRM policy, using dual variables.
result Superior trade-off between mean, minimum, and 5th percentile rates.

Graph neural networks optimize radio resource management policies for wireless networks.

problem Optimizing user selection and power control in wireless networks with fairness constraints.
method Formulated as a Lagrangian dual problem, RRM policies are parameterized by a GNN architecture trained on channel conditions.
result The method achieves superior tradeoff between average and 5th percentile rates, demonstrating fairness.

DefNet defends GNNs against adversarial attacks by identifying and mitigating vulnerabilities.

problem Vulnerability of GNNs to adversarial attacks.
method Investigates latent vulnerabilities in GNN layers, proposes dual-stage aggregation and bottleneck perceptron, and uses adversarial contrastive learning for training.
result DefNet significantly improves GNN robustness under various adversarial attacks.

For a graph embedded into a surface, we relate many combinatorial parameters of the cycle matroid of the graph and the bond matroid of the dual graph with the topological parameters of the embedding. This will give an expression of the polynomial, defined by M.Las Vergnas in a combinatorial way using matroids as a spec…

2010-12-22abs ↗pdf ↗