Relations Are Channels: Knowledge Graph Embedding via Kraus Decompositions

• URL: http://arxiv.org/abs/2605.10317v1
• Date: Mon, 11 May 2026 10:17:52 GMT
• Title: Relations Are Channels: Knowledge Graph Embedding via Kraus Decompositions
• Abstract summary: Knowledge graph embedding (KGE) models typically represent each relation as an operator on entity embeddings.<n>We show that axioms that any principled relation operator must satisfy, linearity, trace preservation, and complete positivity, characterize a Kraus channel structure.<n>We propose textscKrausKGE, a principled KGE model that naturally handles $1$-to-$N$ and $N$-to-$N$ relations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge graph embedding (KGE) models typically represent each relation as an operator on entity embeddings. In this work, we identify three structural axioms that any principled relation operator must satisfy, linearity, trace preservation, and complete positivity, and show that they characterize a Kraus channel structure via the Kraus representation theorem. The completeness constraint defining this family is equivalent to these axioms, providing a principled foundation rather than an externally imposed condition. Under this formulation, most existing operator-based KGE models are recoverable as special cases with Kraus rank $κ= 1$ under specific embedding choices. We further generalize this characterization to arbitrary metric geometries by introducing \mbox{w-Kraus} channels, which satisfy completeness by construction within their respective spaces. Building on this theory, we propose \textsc{KrausKGE}, a principled KGE model that naturally handles $1$-to-$N$ and $N$-to-$N$ relations, supports $k$-hop reasoning without requiring explicit path encoders, and eliminates the need for norm constraints on entity embeddings. Additionally, our framework yields the first theoretically grounded per-relation complexity measure in the KGE literature, with a provable lower bound in terms of the empirical relation matrix rank. Empirical evaluation demonstrates that \textsc{KrausKGE} consistently outperforms strong baselines on $N$-to-$N$ relations, with performance gains that increase monotonically with relation fan-out, in alignment with theoretical predictions.

Related papers

• Quantum correlations in QBism's reconstruction program [0.8594140167290097]
  QBism recasts quantum theory as a normative framework for an agent's probability assignments, with the Born rule taking the form of a consistency condition known as the Urgleichung.<n>Motivated by this perspective, qplex theories provide a broader class of probabilistic models in which the sets of valid states and measurements are constrained by QBist-inspired geometric conditions.
  arXiv  Detail & Related papers  (2026-06-05T17:39:45Z)
• Regularized Online RLHF with Generalized Bilinear Preferences [68.44113000390544]
  We consider the problem of contextual online RLHF with general preferences.<n>We adopt the Generalized Bilinear Preference Model to capture preferences via low-rank, skew-symmetric matrices.<n>We prove that the dual gap of the greedy policy is bounded by the square of the estimation error.
  arXiv  Detail & Related papers  (2026-02-26T15:27:53Z)
• Towards A Unified PAC-Bayesian Framework for Norm-based Generalization Bounds [63.47271262149291]
  We propose a unified framework for PAC-Bayesian norm-based generalization.<n>The key to our approach is a sensitivity matrix that quantifies the network outputs with respect to structured weight perturbations.<n>We derive a family of generalization bounds that recover several existing PAC-Bayesian results as special cases.
  arXiv  Detail & Related papers  (2026-01-13T00:42:22Z)
• Riemannian Zeroth-Order Gradient Estimation with Structure-Preserving Metrics for Geodesically Incomplete Manifolds [57.179679246370114]
  We construct metrics that are geodesically complete while ensuring that every stationary point under the new metric remains stationary under the original one.<n>An $$-stationary point under the constructed metric $g'$ also corresponds to an $$-stationary point under the original metric $g'$.<n>Experiments on a practical mesh optimization task demonstrate that our framework maintains stable convergence even in the absence of geodesic completeness.
  arXiv  Detail & Related papers  (2026-01-12T22:08:03Z)
• A Geometric Approach to Strongly Correlated Bosons: From $N$-Representability to the Generalized BEC Force [12.368400057425]
  Building on recent advances in reduced density matrix theory, we develop a geometric framework for describing strongly correlated lattice bosons.<n>We first establish that translational symmetry, together with a fixed pair interaction, enables an exact functional formulation expressed solely in terms of momentum occupation numbers.
  arXiv  Detail & Related papers  (2026-01-04T20:10:59Z)
• SKGE: Spherical Knowledge Graph Embedding with Geometric Regularization [0.0]
  We propose Spherical Knowledge Graph Embedding (SKGE), a model that constrains entity representations to a compact manifold: a hypersphere.<n>We demonstrate that SKGE consistently and significantly outperforms its strong Euclidean counterpart, TransE.
  arXiv  Detail & Related papers  (2025-11-04T10:40:46Z)
• A Foundational Theory of Quantitative Abstraction: Adjunctions, Duality, and Logic for Probabilistic Systems [2.362412515574206]
  Large or continuous state spaces make exact analysis intractable and call for principled quantitative abstraction.<n>This work develops a unified theory of such abstraction by integrating category theory, coalgebra, quantitative logic, and optimal transport.
  arXiv  Detail & Related papers  (2025-10-22T10:16:24Z)
• Neural Expectation Operators [2.1756081703276]
  This paper introduces textbfMeasure Learning, a paradigm for modeling ambiguity via non-linear expectations.<n>We define Neural Expectation Operators as solutions to Backward Differential Equations (BSDEs) whose drivers are parameterized by neural networks.<n>We provide constructive methods for enforcing key axiomatic properties, such as convexity, by architectural design.
  arXiv  Detail & Related papers  (2025-07-13T06:19:28Z)
• Approximation Rates in Besov Norms and Sample-Complexity of Kolmogorov-Arnold Networks with Residual Connections [9.817834520159936]
  Kolmogorov-Arnold Networks (KANs) have emerged as an improved backbone for most deep learning frameworks.<n>We show that KANs can optimally approximate any Besov function in $Bs_p,q(mathcalX)$ on a bounded open, or even fractal, domain.
  arXiv  Detail & Related papers  (2025-04-21T14:02:59Z)
• A Comprehensive Study on Knowledge Graph Embedding over Relational Patterns Based on Rule Learning [49.09125100268454]
  Knowledge Graph Embedding (KGE) has proven to be an effective approach to solving the Knowledge Completion Graph (KGC) task. Relational patterns are an important factor in the performance of KGE models. We introduce a training-free method to enhance KGE models' performance over various relational patterns.
  arXiv  Detail & Related papers  (2023-08-15T17:30:57Z)
• ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion [78.8942067357231]
  ExpressivE embeds pairs of entities as points and relations as hyper-parallelograms in the virtual triple space. We show that ExpressivE is competitive with state-of-the-art KGEs and even significantly outperforms them on W18RR.
  arXiv  Detail & Related papers  (2022-06-08T23:34:39Z)
• Controlling the Complexity and Lipschitz Constant improves polynomial nets [55.121200972539114]
  We derive new complexity bounds for the set of Coupled CP-Decomposition (CCP) and Nested Coupled CP-decomposition (NCP) models of Polynomial Nets. We propose a principled regularization scheme that we evaluate experimentally in six datasets and show that it improves the accuracy as well as the robustness of the models to adversarial perturbations.
  arXiv  Detail & Related papers  (2022-02-10T14:54:29Z)
• CSNE: Conditional Signed Network Embedding [77.54225346953069]
  Signed networks encode positive and negative relations between entities such as friend/foe or trust/distrust. Existing embedding methods for sign prediction generally enforce different notions of status or balance theories in their optimization function. We introduce conditional signed network embedding (CSNE) Our probabilistic approach models structural information about the signs in the network separately from fine-grained detail.
  arXiv  Detail & Related papers  (2020-05-19T19:14:52Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.