Related papers: Knowledge Graph Completion with Mixed Geometry Tensor Factorization

Knowledge Graph Completion with Mixed Geometry Tensor Factorization

URL: http://arxiv.org/abs/2504.02589v1
Date: Thu, 03 Apr 2025 13:54:43 GMT
Title: Knowledge Graph Completion with Mixed Geometry Tensor Factorization
Authors: Viacheslav Yusupov, Maxim Rakhuba, Evgeny Frolov,
Abstract summary: We propose a new geometric approach for knowledge graph completion via low rank tensor approximation.<n>We augment a pretrained and well-established Euclidean model based on a Tucker tensor decomposition with a novel hyperbolic interaction term.
Score: 0.6827423171182154
License: http://creativecommons.org/licenses/by/4.0/
Abstract: In this paper, we propose a new geometric approach for knowledge graph completion via low rank tensor approximation. We augment a pretrained and well-established Euclidean model based on a Tucker tensor decomposition with a novel hyperbolic interaction term. This correction enables more nuanced capturing of distributional properties in data better aligned with real-world knowledge graphs. By combining two geometries together, our approach improves expressivity of the resulting model achieving new state-of-the-art link prediction accuracy with a significantly lower number of parameters compared to the previous Euclidean and hyperbolic models.

Related papers

CombAlign: Enhancing Model Expressiveness in Unsupervised Graph Alignment [19.502687203792547]
Unsupervised graph alignment finds the node correspondence between a pair of graphs attributed by only exploiting graph structure and node features. One category of recent studies first computes the node representation and then matches nodes with the largest embedding-based similarity. The other category reduces the problem to optimal transport (OT) via Gromov-Wasserstein learning. We investigate the model's discriminative power in distinguishing matched and unmatched node pairs across two graphs. Motivated by our theoretical analysis, we put forward a hybrid approach named CombAlign with stronger expressive power.
arXiv Detail & Related papers (2024-06-19T04:57:35Z)
Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs [22.64740740462169]
We propose a hypergraph learning framework named LFH that is capable of dynamic hyperedge construction and attentive embedding update.<n>To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets.
arXiv Detail & Related papers (2023-07-07T06:26:44Z)
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression [53.15502562048627]
Recent work has built the connection between self-supervised learning and the approximation of the top eigenspace of a graph Laplacian operator. This work delves into a statistical analysis of augmentation-based pretraining.
arXiv Detail & Related papers (2023-06-01T15:18:55Z)
Skeleton Regression: A Graph-Based Approach to Estimation with Manifold Structure [1.2891210250935148]
We introduce a new regression framework designed to deal with large-scale, complex data that lies around a low-dimensional manifold with noises. Our approach first constructs a graph representation, referred to as the skeleton, to capture the underlying geometric structure. We then define metrics on the skeleton graph and apply nonparametric regression techniques, along with feature transformations based on the graph, to estimate the regression function.
arXiv Detail & Related papers (2023-03-19T21:45:40Z)
Joint Graph and Vertex Importance Learning [47.249968772606145]
We propose a novel method to learn a graph with smaller edge weight upper bounds compared to Laplacian approaches. Experimentally, our approach yields much sparser graphs compared to a Laplacian approach, with a more interpretable model.
arXiv Detail & Related papers (2023-03-15T12:12:13Z)
Data-heterogeneity-aware Mixing for Decentralized Learning [63.83913592085953]
We characterize the dependence of convergence on the relationship between the mixing weights of the graph and the data heterogeneity across nodes. We propose a metric that quantifies the ability of a graph to mix the current gradients. Motivated by our analysis, we propose an approach that periodically and efficiently optimize the metric.
arXiv Detail & Related papers (2022-04-13T15:54:35Z)
Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations [57.15855198512551]
We propose a novel score-based generative model for graphs with a continuous-time framework. We show that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule.
arXiv Detail & Related papers (2022-02-05T08:21:04Z)
A Model for Multi-View Residual Covariances based on Perspective Deformation [88.21738020902411]
We derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups. We validate our model with synthetic and real data and integrate it into photometric and feature-based Bundle Adjustment.
arXiv Detail & Related papers (2022-02-01T21:21:56Z)
T-LoHo: A Bayesian Regularization Model for Structured Sparsity and Smoothness on Graphs [0.0]
In graph-structured data, structured sparsity and smoothness tend to cluster together. We propose a new prior for high dimensional parameters with graphical relations. We use it to detect structured sparsity and smoothness simultaneously.
arXiv Detail & Related papers (2021-07-06T10:10:03Z)
Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference [48.63194907060615]
We build off of semi-implicit graph variational auto-encoders to capture higher-order statistics in a low-dimensional graph latent representation. We incorporate hyperbolic geometry in the latent space through a Poincare embedding to efficiently represent graphs exhibiting hierarchical structure.
arXiv Detail & Related papers (2020-10-31T05:48:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.