We develop meta-path embeddings to improve feature learning in heterogeneous knowledge graphs.
problem Redundant and unsuitable categorical features in meta-paths for machine learning models.
method Skipgram model with meta-path extension for learning semantical and compact vector representations.
result Meta-path embeddings improve link prediction on Wikidata.
Task-guided network embedding improves author identification accuracy.
problem Identifying authors from anonymized papers in double-blind review settings.
method Task-guided and path-augmented heterogeneous network embedding model.
result Significantly better accuracy in identifying true authors compared to existing methods.
MEGA and MEGA++ embed meta-paths and meta-graphs for better network similarity.
problem Ignoring meta-paths in meta-graph-based relevance computing.
method MEGA++ uses tensor decomposition and coupled tensor-matrix decomposition for joint node embedding.
result MEGA and MEGA++ outperform state-of-the-art approaches in similarity search.
The classical theorem of Fáry states that every planar graph can be represented by an embedding in which every edge is represented by a straight line segment. We consider generalizations of Fáry's theorem to surfaces equipped with Riemannian metrics. In this setting, we require that every edge is drawn as a shortest pa…
Landmark-based node embeddings approximate shortest path distances in random graphs.
problem Capturing global graph distances in node representations.
method Landmark-based node embeddings using shortest path distances from a subset of reference nodes (landmarks).
result Random graphs require lower dimensions in landmark-based embeddings compared to worst-case graphs.
Probabilistic McShane's identity measures paths through a point.
problem Understanding the probabilistic nature of McShane's identity.
method Interpreting McShane's identity as a measure on path spaces.
result A probabilistic measure on path spaces.
A new method for embedding heterogeneous networks using spacey random walks.
problem Stationarity issues in meta-path guided random walks for HIN embedding.
method Heterogeneous personalized spacey random walk.
result Substantial improvement over existing network embedding algorithms.
Deep learning approximates shortest path distances in large graphs.
problem Scaling up shortest path distance computation in large networks.
method Deep learning techniques to approximate distances using vector embeddings.
result Feedforward neural networks with embeddings can approximate distances with low distortion error.
A novel signature method improves sequential data prediction accuracy.
problem Improving prediction accuracy for sequential and temporal data.
method Signature method based on rough path theory, with a specific embedding called lead-lag.
result Lead-lag embedding consistently outperforms other embeddings across various datasets and algorithms.
New analysis of annealing paths in sampling and estimation.
problem Sampling from complex distributions and estimating normalization constants.
method Extending known results on Bregman divergence to quasi-arithmetic means under monotonic embedding.
result Analogous result for quasi-arithmetic means, highlighting the interplay between means, parametric families, and divergence functionals.
EntroPath learns manifold geometry from diffusion paths.
problem Learning geodesic geometry from data graphs with spurious shortcuts.
method Maximum Entropy Path Ensemble Embedding (MERW) with k-step diffusion paths.
result EntroPath converges to squared geodesic distance in the short-time limit.
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.
C-RSP embeds multi-view graphs using randomized shortest paths.
problem Combining multiple views of a graph to improve inference quality.
method C-RSP algorithm that generates a common embedding using RSP.
result C-RSP outperforms benchmarks in embedding and clustering tasks.
Predicts path failures in evolving networks using deep learning.
problem Predicting path failures in time-evolving graphs.
method LRGCN, SAPE
result LRGCN outperforms other methods in path failure prediction.
We prove that the moduli space of 2-convex embedded n-spheres in R^{n+1} is path-connected for every n. Our proof uses mean curvature flow with surgery and can be seen as an extrinsic analog to Marques' influential proof of the path-connectedness of the moduli space of positive scalar curvature metics on three-manifold…
This work proposes a hybrid method for error detection in noisy Knowledge Graphs.
problem Error detection in noisy Knowledge Graphs.
method Hybrid and modular approach combining path ranking and representation learning.
result Hybrid method outperforms individual methods on benchmarks and real-world dataset.
New framework for manifold convolutions using toric embeddings.
problem Computational intractability of manifold convolutions.
method Isometric embeddings into tori for global manifold convolutions.
result Global definition of manifold convolutions on finite approximations.
For a finite simplicial graph Γ, let G(Γ) denote the right-angled Artin group on the complement graph of Γ. In this article, we introduce the notions of "induced path lifting property" and "semi-induced path lifting property" for immersions between graphs, and obtain graph theoretical criteria for the embedabilit…
Interstellar searches for recurrent architecture to enhance KG embedding.
problem Learning long-term information in KGs.
method Recurrent neural architecture search for relational paths.
result Effectiveness and efficiency of searched models.
We study the convergence of earthquake paths and horocycle paths in the Gardiner-Masur compactification of Teichmüller space. We show that an earthquake path directed by a uniquely ergodic or simple closed measured geodesic lamination converges to the Gardiner-Masur boundary. Using the embedding of flat metrics into th…
The paper extends isometric embedding results to null cones and spheres.
problem Isometric embedding of metrics on spheres in null cones.
method Extending Li-Wang's result to compact manifolds, specializing to 2D, developing existence and uniqueness theorems, and proving foliations.
result Existence and uniqueness of isometric embeddings in null cones.
Matching datasets of multiple modalities has become an important task in data analysis. Existing methods often rely on the embedding and transformation of each single modality without utilizing any correspondence information, which often results in sub-optimal matching performance. In this paper, we propose a nonlinear…
We present an embedding of stochastic optimal control problems, of the so called path integral form, into reproducing kernel Hilbert spaces. Using consistent, sample based estimates of the embedding leads to a model free, non-parametric approach for calculation of an approximate solution to the control problem. This fo…
The paper extends Lipschitz metric isometries between Outer Spaces of virtually free groups.
problem Extending isometry properties of Lipschitz metric to virtually free groups.
method Analyzing finite-index subgroups and their covers, identifying folding paths, and using deformation retraction.
result Existence of candidates for Lipschitz distance and deformation retraction of spine.
PathRank ranks paths in spatial networks using multi-task learning.
problem Ranking paths in spatial networks for better navigation services.
method Data-driven framework using multi-task learning, spatial network embedding, and recurrent neural networks.
result PathRank effectively ranks paths based on historical trajectories.
Graph embedding method captures both local and global network structure.
problem Representing and analyzing complex graph networks.
method Spectral embedding based on a generalized graph Laplacian.
result Significant improvement in data analysis tasks.
An almost complex structure J on a 4-manifold X may be described in terms of a rank 2 vector bundle E. A splitting of J consists of a pair of line bundles spanning E. A hypersurface M in X satisfying a nondegeneracy condition inherits a CR-structure from J and a path geometry from the splitting. Using the Cartan-Kähler…
Proposes a method to improve graph embedding by removing least frequent nodes.
problem Capturing global graph structure in random walk-based embeddings.
method Extends random walk-based graph embedding by removing least frequent nodes.
result Improves predictive performance slightly, if at all.
New bounds on knotting probability of equilateral hexagons found.
problem Determining the knotting probability of equilateral hexagons.
method Symplectic geometry techniques to parametrize and analyze the space of equilateral hexagons.
result New bounds on the knotting probability of equilateral hexagons.
Study shows path-connectedness of tori moduli space for n≥3 and knot class correspondence for n=2.
problem Topology of moduli space of two-convex embedded tori.
method Variant of mean curvature flow with surgery, preserving topology, embeddedness, and two-convexity.
result Proves path-connectedness for n≥3 and knot class correspondence for n=2.
Knowledge base (KB) completion adds new facts to a KB by making inferences from existing facts, for example by inferring with high likelihood nationality(X,Y) from bornIn(X,Y). Most previous methods infer simple one-hop relational synonyms like this, or use as evidence a multi-hop relational path treated as an atomic f…
We prove that each sub-Riemannian manifold can be embedded in some Euclidean space preserving the length of all the curves in the manifold. The result is an extension of Nash C1 Embedding Theorem. For more general metric spaces the same result is false, e.g., for Finsler non-Riemannian manifolds. However, we also sh…
Study on Frechet distance properties for paths and graphs.
problem Understanding topological properties of Frechet distance spaces.
method Proving path-connectedness of Frechet distance spaces and metric balls.
result Spaces of paths and graphs under Frechet distance are path-connected.
Unified representation for tree ensembles indexed by nodes
problem Unifying geometric object for tree ensembles indexed by nodes
method KPP indexes feature map by nodes, weighted by path metric
result Unified non-diagonal Gram for prediction, additive attribution, robust radius, and risk bounds
This paper proposes grid cells encode position via a conformal isometric embedding of 2D physical space.
problem Hexagonal grid firing patterns in grid cells.
method Learning a distance-preserving position embedding in neural space using a recurrent neural network.
result The conformal isometric embedding of 2D physical space into neural space explains hexagonal grid firing patterns.
Model place cells as spatial embeddings for efficient path planning and cognitive map construction.
problem Encoding spatial navigation in the hippocampus.
method Model place cells using spectral decomposition of multi-step random walk transition kernels, inducing sparsity and adjacency.
result Place cells encode spatial information through non-negativity and inner-product structure, forming a cognitive map.
The paper proves properties of minimal isometric embeddings and conformal deformations of Riemannian surfaces.
problem Minimal isometric embeddings and conformal deformations of Riemannian surfaces.
method Analyzes minimal isometric embeddings and conformal deformations of Riemannian surfaces.
result Minimal isometric embeddings and conformal deformations of Riemannian surfaces have specific properties.
Proposes HetSANN for learning heterogeneous graph structures without meta-paths.
problem Learning low-dimensional vector space of heterogeneous information networks.
method Implicitly represents heterogeneous information through entity space transformation and attention mechanism.
result Significant improvements over state-of-the-art solutions on public datasets.
PSLR classifies functional data with scalar covariates using path signatures.
problem Classical functional logistic regression models have limitations in capturing nonlinear and cross-channel dependencies.
method PSLR uses truncated path signatures to create a basis-free representation of functional data.
result PSLR outperforms traditional functional classifiers in accuracy and robustness, especially under non-uniform sampling.
Path queries on a knowledge graph can be used to answer compositional questions such as "What languages are spoken by people living in Lisbon?". However, knowledge graphs often have missing facts (edges) which disrupts path queries. Recent models for knowledge base completion impute missing facts by embedding knowledge…
Neural RDEs extend CDEs to irregular time series.
problem Modeling long irregular time series efficiently.
method Representing time series through log-signature and solving RDEs.
result Significant training speed-ups and improved model performance.
We use the criteria of Lalonde and McDuff to determine a new class of examples of length minimizing paths in the group Ham(M). For a compact symplectic manifold M of dimension two or four, we show that a path in Ham(M), generated by an autonomous Hamiltonian and starting at the identity, which induces no non-cons…
The symmetries of paths in a manifold M are classified with respect to a given pointwise proper action of a Lie group G on M. Here, paths are embeddings of a compact interval into M. There are at least two types of symmetries: Firstly, paths that are parts of an integral curve of a fundamental vector field on $…
We generalize the notion of parallel transport along paths for abelian bundles to parallel transport along surfaces for abelian gerbes using an embedded Topological Quantum Field Theory (TQFT) approach. We show both for bundles and gerbes with connection that there is a one-to-one correspondence between their local des…
The paper analyzes how grid cells perform path integration and learns hexagon grid patterns.
problem Understanding how grid cells perform path integration calculations.
method Theoretical analysis of a general representation model of path integration by grid cells, identifying group representation and isotropic scaling conditions.
result The learned model of hexagon grid patterns is capable of accurate long distance path integration.
Generative model for TPPs using signatures and distributional discrepancies.
problem Limitations of signature methods for TPPs and lack of global sequence-level loss in neural models.
method Introduce interarrival embedding to lift jump paths to continuous paths of bounded variation, enabling signature methods for discrete event sequences. Develop sigTPP, a signature-based generative model trained on path-level loss.
result sigTPP achieves the best average rank across multiple metrics and outperforms or is within a standard error of the strongest baseline in 64% of dataset-metric pairs.
Evolution equations for paths on manifolds with anisotropic weights and constraints.
problem Inference on non-trivial covariance manifold-valued data.
method Anisotropically weighted curve energies, sub-Riemannian metrics, geodesics, stochastic development.
result Evolution equations derived for paths on manifolds, connecting to geodesics and polynomials.
Authors create déjà vu links in Legendrian geometry.
problem Understanding déjà vu moments in spacetime.
method Constructing Legendrian links with specific properties.
result Found examples of déjà vu links in various geometric settings.