Generative Link Sequence Modeling predicts future links in evolving networks.
problem Predicting future links in networks with evolving structures.
method Sequence modeling framework with self-tokenization to capture temporal link formation patterns.
result GLSM achieves best performance on AUC metrics compared to existing methods.
The paper examines linking numbers in grid models and finds polynomial moments.
problem Analyzing linking numbers in grid models.
method Examined linking numbers as a random variable on isotopy classes of 2-component links, computed moments and limits.
result The uth moment of the linking number is a polynomial in the grid size with degree d≤u, and all odd moments vanish. New model for links uses meander diagrams and combinatorics.
problem Modeling and analyzing random links.
method Random meander model based on meander diagrams and graphs, proving properties using combinatorics.
result Trivial links are unlikely, and there's a lower bound on non-isotopic knots.
Develops a new causal model for path-dependent link prediction.
problem Existing causal models assume fixed node factors, but real-world links can depend on existing ones.
method Introduces causal lifting and structural pairwise embeddings for path-dependent link prediction.
result Validated on three scenarios, demonstrating improved accuracy for causal link prediction.
Aicardi's invariant F(L) is extended to colored singular links using graphical calculus.
problem Constructing an invariant for colored classical and singular links.
method State-sum model using graphical calculus for oriented, colored, 4-valent planar graphs.
result Extends F(L) to colored singular links, showing it's stronger than HOMFLY-PT polynomial. A. S. Lipson constructed two state models yielding the same classical link invariant obtained from the Kauffman polynomial F(a,z). In this paper, we apply Lipson's state models to marked graph diagrams of surface-links, and observe when they induce surface-link invariants.
Recurrent Neural Networks (RNNs) have been proven to be effective in modeling sequential data and they have been applied to boost a variety of tasks such as document classification, speech recognition and machine translation. Most of existing RNN models have been designed for sequences assumed to be identically and ind…
FakeEdge tackles dataset shift in link prediction tasks.
problem Dataset shift between training and testing sets in link prediction.
method Model-agnostic technique to mitigate graph topological gap.
result Extensive experiments show FakeEdge's superiority on multiple datasets.
We study random knots and links in R^3 using the Petaluma model, which is based on the petal projections developed by Adams et al. (2012). In this model we obtain a formula for the distribution of the linking number of a random two-component link. We also obtain formulas for the expectations and the higher moments of t…
DEAL model predicts links for new nodes with only attribute info.
problem Predicting links for new nodes with only attribute info.
method DEAL model with two encoders and alignment mechanism.
result DEAL significantly outperforms existing methods on inductive link prediction.
Proposes a method to enhance graph models by injecting unseen connections.
problem Enhancing graph models to utilize unseen connections.
method Parametric link injection layer to find and inject weak connections.
result Improves performance on node classification and link prediction tasks.
The paper confirms a conjecture linking link bipyramid volume and Mahler measure.
problem Link bipyramid volume and Mahler measure relationship for alternating links.
method Using isoradial graphs and spanning trees on lattices, the authors confirm the conjecture for two examples and calculate five more.
result The conjecture is confirmed for specific examples of alternating links.
We construct a 2-variable link polynomial, called WL, for classical links by considering simultaneously the Kauffman state models for the Alexander and for the Jones polynomials. We conjecture that this polynomial is the product of two 1-variable polynomials, one of which is the Alexander polynomial. We refine WL…
Latent topic models have been successfully applied as an unsupervised topic discovery technique in large document collections. With the proliferation of hypertext document collection such as the Internet, there has also been great interest in extending these approaches to hypertext [6, 9]. These approaches typically mo…
GEN tackles few-shot out-of-graph link prediction in evolving multi-relational graphs.
problem Predicting links between unseen nodes in evolving multi-relational graphs with few edges per node.
method Transductive meta-learning framework (GEN) for inductive and transductive inference.
result GEN significantly outperforms relevant baselines for out-of-graph link prediction tasks.
Improves biomedical entity linking with latent type modeling.
problem Lack of fine-grained type information for entity disambiguation.
method Jointly models entity disambiguation and latent type learning without direct supervision.
result Significant performance improvements over state-of-the-art techniques.
Paper introduces symmetric divergence link models for probability distributions.
problem Symmetric divergence measures for probability distributions.
method Two general classes of link models: one for survival functions and another for cumulative probability distribution functions.
result Advantages of symmetric divergence measures over asymmetric measures for model averaging and feature assessment.
NPGNN improves graph link prediction by adapting to new graphs.
problem Inductive link prediction in graphs with limited training data.
method Meta-learning with graph neural networks (NPGNN).
result NPGNN outperforms state-of-the-art models in real-world graphs.
GENN predicts drug interactions by modeling correlations between link labels.
problem Predicting drug-drug interactions with consideration of link type correlations.
method GENN uses graph energy neural networks to model link type correlations in DDI prediction.
result GENN outperforms baseline models by 13.77% and 5.01% in PR-AUC on two real-world datasets.
The paper studies pseudo links in genus g handlebodies, generalizing knot theory.
problem Modeling DNA knots with missing crossing information.
method Introducing pseudo links as mixed pseudo links in S^3, generalizing Kauffman bracket polynomial and Alexander theorem.
result The theory of pseudo links is closely related to singular links and can be applied to study singular links in genus g handlebodies.
Bayesian MS-VAR model for pricing equity-linked life insurance products.
problem Pricing and hedging equity-linked life insurance products on maximum of several assets.
method Introduces Bayesian Markov-Switching Vector Autoregressive (MS-VAR) process to model economic variables and insured's lifetime.
result Obtains net single premiums and hedging formulas for equity-linked life insurance products.
Topological model created for HOMFLY-PT polynomial from link diagrams.
problem Constructing categorifications for HOMFLY-PT polynomial.
method Explicit Lagrangian submanifolds on Heegaard surfaces.
result Invariants derived from link diagrams are given by intersections of submanifolds.
New method optimizes policies without assuming known link functions between preferences and rewards.
problem Policy alignment with unknown and unrestricted link functions.
method Formulates an f-divergence-constrained reward maximization problem, learning policies directly. result Induces a semiparametric single-index binary choice model for policy alignment.
We employ a solution of the Yang-Baxter equation to construct invariants for knot-like objects. Specifically, we consider a Yang-Baxter state model for the sl(n) polynomial of classical links and extend it to oriented singular links and balanced oriented 4-valent knotted graphs with rigid vertices. We also define a rep…
Random walks and polygons are used to model polymers. In this paper we consider the extension of writhe, self-linking number and linking number to open chains. We then study the average writhe, self-linking and linking number of random walks and polygons over the space of configurations as a function of their length. W…
This paper aims at the problem of link pattern prediction in collections of objects connected by multiple relation types, where each type may play a distinct role. While common link analysis models are limited to single-type link prediction, we attempt here to capture the correlations among different relation types and…
Proposes a novel tensor-based approach for multi-level link prediction.
problem Inferring potential links from observed networks.
method Tensor-based joint network embedding capturing pairwise and hyperlinks.
result Improves hyperlink and pairwise link prediction accuracy.
Study Alexander polynomials of special alternating links and generalize Fox's conjecture.
problem Distinguish special alternating links up to isotopy using polynomial invariants.
method Combinatorial and discrete geometric properties of Alexander polynomials of special alternating links.
result Generalized Alexander polynomials of special alternating links can be expressed in terms of volumes of root polytopes of unimodular matrices.
Random hyperbolic 3-manifolds can be obtained via Dehn surgery.
problem Understanding the generic properties of hyperbolic 3-manifolds.
method Counting model on links and Dehn surgeries.
result Random hyperbolic 3-manifolds can be obtained via Dehn surgery.
New model values equity-linked securities with guaranteed return.
problem Valuation of equity-linked securities with guaranteed return.
method Replicate security price as sum of guaranteed amount and Asian style option price on basket.
result Analytical formulas derived for security price and hedge ratios.
We are concerned with modeling the strength of links in networks by taking into account how often those links are used. Link usage is a strong indicator of how closely two nodes are related, but existing network models in Bayesian Statistics and Machine Learning are able to predict only wether a link exists at all. As …
Study tackles nonlinear factor models with unknown monotone links from incomplete and noisy data.
problem Learning nonlinear factor models with unknown monotone links from incomplete and noisy data.
method Formulated as joint recovery of low-rank factors, loadings, and nonlinear link function; proposed BCD algorithm with regularization.
result Established convergence guarantees and sublinear regret bounds for link-function updates.
Link prediction is an important way to complete knowledge graphs (KGs), while embedding-based methods, effective for link prediction in KGs, perform poorly on relations that only have a few associative triples. In this work, we propose a Meta Relational Learning (MetaR) framework to do the common but challenging few-sh…
Using a simplistic model of juggling based on physics, a natural map is constructed from the set of periodic juggling patterns (or site swaps) to links. We then show that all topological links can be juggled.
Graph Convolutional Networks (GCNs) have proved to be a most powerful architecture in aggregating local neighborhood information for individual graph nodes. Low-rank proximities and node features are successfully leveraged in existing GCNs, however, attributes that graph links may carry are commonly ignored, as almost …
Stacked models improve link prediction across diverse networks.
problem Predicting missing links in complex networks.
method Systematically evaluated 203 link predictor algorithms, combining them into stacked models.
result Stacked models achieve optimal or nearly optimal link prediction accuracy.
Graph Convolutional Gaussian Processes predict missing links.
problem Link prediction in large graphs.
method Simplified graph convolutions and variational inducing point method.
result Consistent improvements over existing models and competitive performance.
Proposes a new model for high-dimensional data analysis with unknown link function.
problem Estimating link function, component functions, and variable interactions in high-dimensional data.
method Generalized Sparse Additive Model with Unknown Link Function (GSAMUL) using B-spline basis and MLP network for link estimation, with ℓ2,1-norm regularizer for variable selection. result Can realize both variable selection and hidden interaction.
State surfaces are spanning surfaces of links that are obtained from link diagrams guided by the combinatorics underlying Kauffman's construction of the Jones polynomial via state models. Geometric properties of such surfaces are often dictated by simple link diagrammatic criteria, and the surfaces themselves carry imp…
This paper describes a method to obtain state model parameters for an infinite series of Links-Gould link invariants LG^{m,n}, based on quantum R matrices associated with the (\dot{0}_m | \dotα_n) representations of the quantum superalgebras U_q[gl(m|n)]. Explicit details of the state models for the cases n=1 and m=1,2…
NePTuNe combines neural and tensor methods for efficient link prediction in knowledge graphs.
problem Incomplete knowledge graphs, especially in link prediction.
method Hybrid model combining neural and tensor factorization methods.
result NePTuNe achieves state-of-the-art performance on FB15K-237 and near state-of-the-art on WN18RR datasets.
Proposes a new tensor factorization model for better link prediction in knowledge graphs.
problem Lack of information in treating missing and non-existing relations equally in tensor factorization models.
method Introduces a binary tensor factorization model with probit link to address the issue.
result Shows improved prediction accuracy and interpretability compared to existing models.
GG-SAGE predicts links in directed graphs with attributes, outperforming existing methods.
problem Predicting links in directed graphs with node attributes.
method Gravity-GraphSAGE, a modified GraphSAGE model with a gravity-inspired decoder.
result GG-SAGE outperforms state-of-the-art GDL link prediction techniques.
Abstract summarizes level-rank duality in knot and link invariants.
problem Distinguishing torus knots and links from hyperbolic ones.
method Chern-Simons theory and tables of knot invariants.
result Criterion to distinguish torus knots and links from hyperbolic ones.
Link prediction is a fundamental task in statistical network analysis. Recent advances have been made on learning flexible nonparametric Bayesian latent feature models for link prediction. In this paper, we present a max-margin learning method for such nonparametric latent feature relational models. Our approach attemp…
We study the spaces of string links and homotopy string links in an arbitrary manifold using multivariable manifold calculus of functors. We construct multi-cosimplicial models for both spaces and deduce certain convergence properties of the associated Bousfield-Kan homotopy and cohomology spectral sequences when the a…
Classifies L-space surgeries on all two-bridge links
problem Classifying L-space surgeries on two-bridge links method Introduces a sufficient diagrammatic condition for links in S3 to be persistently foliar, defines a simplified model for Heegaard Floer homology, and uses Turaev torsions for computations result Determines L-space surgeries in the case of generalised L-space links We extend the state models for Jones and Alexander polynomials of classical links to state models of 2-variable polynomials in the case of singular links. Moreover, we extend both of them to polynomials with d+1 variables for long singular knots with exactly d double points. These extensions can detect non-invertibilit…