LinkNBed learns entity and relationship representations across multiple graphs.
problem Jointly learn over multiple graphs and construct a unified graph.
method LinkNBed is a deep relational learning framework that learns entity and relationship representations across multiple graphs. It identifies entity linkage as a vital component and designs a novel objective to leverage it.
result Substantial improvements in link prediction and entity linkage over state-of-the-art relational learning approaches.
Record linkage involves merging records in large, noisy databases to remove duplicate entities. It has become an important area because of its widespread occurrence in bibliometrics, public health, official statistics production, political science, and beyond. Traditional linkage methods directly linking records to one…
This article reviews entity resolution methods and their applications.
problem Integrating information from multiple sources to clean and accurately link records.
method Clustering, semi- and fully supervised methods, canonicalization.
result Modern probabilistic record linkage has been foundational.
Bayesian approach for multifile record linkage and duplicate detection.
problem Challenges in merging overlapping datafiles with duplicates.
method Bayesian approach with novel partition representation and loss functions.
result Proposes a flexible prior for partitions and uncertain unresolved portions.
Entity resolution (ER) is the task of identifying records belonging to the same entity (e.g. individual, group) across one or multiple databases. Ironically, it has multiple names: deduplication and record linkage, among others. In this paper we survey metrics used to evaluate ER results in order to iteratively improve…
d-blink scales Bayesian ER to large datasets.
problem Bayesian ER models struggle with scalability and error in large databases.
method d-blink uses auxiliary variables, k-d trees, and a distributed Gibbs sampler.
result d-blink achieves scalable and accurate Bayesian ER.
STANCE learns string similarity using optimal transport alignment.
problem Computing similarity between strings for record linkage and entity resolution.
method Character encoding, optimal transport alignment, convolutional neural network scoring.
result STANCE outperforms state-of-the-art models on alias detection datasets.
The bipartite record linkage task consists of merging two disparate datafiles containing information on two overlapping sets of entities. This is non-trivial in the absence of unique identifiers and it is important for a wide variety of applications given that it needs to be solved whenever we have to combine informati…
Data of practical interest - such as personal records, transaction logs, and medical histories - are sequential collections of events relevant to a particular source entity. Recent studies have attempted to link sequences that represent a common entity across data sets to allow more comprehensive statistical analyses a…
In record linkage (RL), or exact file matching, the goal is to identify the links between entities with information on two or more files. RL is an important activity in areas including counting the population, enhancing survey frames and data, and conducting epidemiological and follow-up studies. RL is challenging when…
We develop a structural default model for interconnected financial institutions in a probabilistic framework. For all possible network structures we characterize the joint default distribution of the system using Bayesian network methodologies. Particular emphasis is given to the treatment and consequences of cyclic fi…
Two solutions for multi-modal record linkage using Deep Learning inspired by Visual Question Answering.
problem Matching records from multiple sources representing the same entity.
method Two fusion modules: Recurrent Neural Network + Convolutional Neural Network and Stacked Attention Network. A Siamese Neural Network computes similarity.
result Recurrent Neural Network + Convolutional Neural Network fusion module outperforms a simple model.
New model integrates community and link clustering for network data.
problem Lack of embedded prior information and community evolution description in MMSB.
method Fragmentation coagulation process for community and link clustering, with Gibbs sampling for inference.
result Model infers community structure and evolution, improving MMSB.
Method preserves order in hierarchical clustering of ordered data.
problem Order preserving hierarchical clustering of directed acyclic graphs.
method Combination of classical hierarchical clustering and ultrametric fitting.
result Optimal clustering preserves both cluster quality and order.
A new clustering method versatile linkage improves on existing strategies.
problem Improving agglomerative hierarchical clustering methods.
method Introducing versatile linkage, a family of clustering strategies based on generalized means.
result Versatile linkage is space-conserving compared to existing methods.
New method for estimating firm linkages using CVLs and QCML.
problem Estimating firm linkages for profitable trading strategies.
method Characteristic Vector Linkages (CVLs) and Quantum Cognition Machine Learning (QCML).
result QCML similarity outperforms Euclidean similarity in constructing profitable trading strategies.
The geometric, topological, and symplectic properties of moduli spaces (spaces of configurations modulo rotations and translations) of polygonal linkages have been studied by Kapovich, Millson, and Kamiyama, et. al. One can form a polygonal linkage by taking two free linkages and identifying initial and terminal vertic…
Minimax linkage improves clustering interpretability by minimizing maximum distance to prototypes.
problem Improving clustering interpretability and performance.
method Uses distances to prototypes for cluster formation, evaluated on multiple metrics.
result Minimax linkage often produces the smallest maximum minimax radius, but not always best across all metrics.
Paper introduces a method for supervised hierarchical clustering with Exponential Linkage.
problem Discrepancy between training and clustering objectives in supervised clustering.
method Tightly couples supervised training of dissimilarity function with hierarchical clustering, using Exponential Linkage.
result Joint training procedure consistently matches or outperforms other methods, improving dendrogram purity by up to 8 points.
This paper studies the configuration space of all possible positions of a linkage in R^n. For example, it shows that for every compact algebraic set, there is a linkage whose configuration space is analytically isomorphic to a finite number of copies of the algebraic set. If flexible edges are allowed, any compact set …
New closed linkage mechanisms with Möbius strip properties.
problem Designing closed linkage mechanisms with arbitrary number of hinges.
method Proposed a new family of closed linkage mechanisms with singular properties.
result These mechanisms can be considered as discrete Möbius strips.
Cryptocurrencies are becoming more linked in their returns and volatilities.
problem Understanding the increasing interconnectivity of cryptocurrencies.
method Examined market linkages using returns and volatilities, applied various methodologies.
result Significant increase in market linkages for both returns and volatilities.
This paper proposes RiskRank as a joint measure of cyclical and cross-sectional systemic risk. RiskRank is a general-purpose aggregation operator that concurrently accounts for risk levels for individual entities and their interconnectedness. The measure relies on the decomposition of systemic risk into sub-components …
Paper addresses limitations of traditional hierarchical clustering methods.
problem Traditional hierarchical clustering methods face limitations in binary trees and ultrametrics.
method Introduces the notion of a valid hierarchy and a two-step algorithm to construct a binary tree and prune it to enforce validity.
result Proposes a method to recover the finest valid hierarchy, which is not constrained to binary structures.
New model detects crime linkages from text, time, and space.
problem Detecting crime linkages from limited information.
method Spatio-temporal-textual Hawkes processes with text embeddings.
result Joint modeling of space, time, and text enhances crime linkage detection.
New method extracts all reliable linkages in agglomerative clustering.
problem Finding optimal clustering solutions with adaptive and flexible criteria.
method Extracting all reliable linkages at each step for various criteria.
result Single linkage criterion yields minimum spanning tree.
Paper analyzes a three-loop linkage, showing it's overconstrained and shaky.
problem Analyzing a three-loop spatial linkage's degree of freedom and configuration space.
method Local analysis of differential degrees of freedom, computation of kinematic tangent cone, and c-space approximation.
result The linkage has a finite degree of freedom 3 and is locally a smooth manifold, making it shaky.
Moduli spaces of planar polygonal linkages admit a cell structure which can be realized as a surgery on the permutohedron. We present a 3D visualization of the result of the surgery for all types of non-degenerate pentagonal linkages.
We prove realizability theorems for vector-valued polynomial mappings, real-algebraic sets and compact smooth manifolds by moduli spaces of planar linkages. We also establish a relation between universality theorems for moduli spaces of mechanical linkages and projective arrangements.
A mechanical linkage is a mechanism made of rigid rods linked together by flexible joints, in which some vertices are fixed and others may move. The partial configuration space of a linkage is the set of all the possible positions of a subset of the vertices. We characterize the possible partial configuration spaces of…
RLINK uses deep reinforcement learning to improve user identity linkage across social networks.
problem Recognizing the same user across different social networks.
method Converts user identity linkage into a sequence decision problem and uses deep reinforcement learning to optimize the linkage strategy.
result Achieves better performance than state-of-the-art methods in experiments on various datasets.
Study examines insurance sector linkages and systemic risk using dynamic spanning trees.
problem Interlinkages and systemic risk in the European insurance sector.
method Analysis of linkage dynamics and systemic risk using correlation networks, copulas, and minimum spanning trees.
result Minimum spanning trees describe linkage dynamics in the European insurance sector.
A linkage is a finite graph with lengths assigned to each edge. A planar realization is a map to the plane which preserves edge lengths. It can be thought of as a mechanical device formed from stiff rods and rotating joints. We look at the configuration space of all planar realizations of a linkage (following work of K…
Paper studies how discrete space curves with constant torsion deform to model linkage motions.
problem Modeling and understanding the motion of discrete space curves with constant torsion.
method Using semi-discrete mKdV equations to describe the motion of discrete space curves.
result The motion of discrete space curves is governed by semi-discrete mKdV equations.
A mechanical linkage is a mechanism made of rigid rods linked together by flexible joints, in which some vertices are fixed and others may move. The partial configuration space of a linkage is the set of all the possible positions of a subset of the vertices. We characterize the possible partial configuration spaces of…
Study explores financial market linkages between Japan and US markets.
problem Inconsistency in empirical studies regarding financial market causal linkages.
method Causal discovery methods including VAR-LiNGAM and LPCMCI with domain knowledge.
result VAR-LiNGAM reveals causal influences among financial markets, while LPCMCI identifies potential latent confounders.
New bounds improve linkage methods for clustering, distinguishing complete-link from single-link.
problem Improving bounds on linkage methods for clustering quality.
method Developed new bounds for complete-link and average-link methods in agglomeration clustering.
result Separated complete-link from single-link in terms of approximation for diameter.
The task of matching co-referent records is known among other names as rocord linkage. For large record-linkage problems, often there is little or no labeled data available, but unlabeled data shows a reasonable clear structure. For such problems, unsupervised or semi-supervised methods are preferable to supervised met…
We study configuration spaces of linkages whose underlying graph are polygons with diagonal constrains, or more general, partial two-trees. We show that (with an appropriate definition) the oriented area is a Bott-Morse function on the configuration space. Its critical points are described and Bott-Morse indices are co…
Hierarchical clustering uses OWA operators to generalize linkage methods and avoid dendrogram inversions.
problem Avoiding unaesthetic inversions in hierarchical clustering dendrograms.
method OWA-based linkages combined with the Lance-Williams formula and conditions on weight generators.
result Conditions for weight generators to produce dendrograms without inversions.
We study spaces of realisations of linkages (weighted graphs) whose underlying graph is a series parallel graph. In particular, we describe an algorithm for determining whether or not such spaces are connected.
We prove diffeomorphisms of polygonal linkage moduli spaces to Euclidean spaces.
problem Moduli spaces of self-avoiding polygonal linkages and configurations.
method Construct Lyapunov-Reeb functions to show diffeomorphisms.
result Moduli spaces are diffeomorphic to Euclidean spaces.
Study maps interdependence of SDGs, finds complex, dynamic linkages.
problem Identify which SDGs promote progress and how quickly.
method Used a balanced panel of 114 countries from 2000 to 2024, applying two estimators to recover directed interaction network and measure dynamic linkages.
result 84 goal linkages survive false-discovery control, showing both synergies and trade-offs, with no single goal acting as a universal accelerator.
Grinch efficiently clusters large datasets with complex structures.
problem Large-scale hierarchical clustering with complex linkage functions.
method Rotate and graft subroutines for efficient reconfiguration.
result Grinch guarantees accurate cluster trees for consistent models.
This paper characterizes which subsets of C^n can be the set of positions of n points on a linkage in the complex plane C. For example, assuming compactness they are just compact semialgebraic sets. Noncompact configuration spaces are semialgebraics sets invariant under the Euclidean group, with compact quotient.
An efficient method to compute a single linkage dendrogram.
problem Computing a single linkage dendrogram efficiently.
method Form an edge-weighted graph, calculate MST, recursively split longest edge.
result Efficiently determine vertices of subtrees without additional cost.
Any smooth surface in R^3 may be flattened along the z-axis, and the flattened surface becomes close to a billiard table in R^2 . We show that, under some hypotheses, the geodesic flow of this surface converges locally uniformly to the billiard flow. Moreover, if the billiard is dispersive and has finite horizon, then …
Proposes a novel classifier for probabilistic record linkage.
problem Probabilistic record linkage across databases.
method Graphical model based on mixture of Poisson distributions with latent variables, using gamma priors and supervised labels.
result Classifier works effectively with sparse and streaming data.