Geometric Relational Embeddings: A Survey

• URL: http://arxiv.org/abs/2304.11949v1
• Date: Mon, 24 Apr 2023 09:33:30 GMT
• Title: Geometric Relational Embeddings: A Survey
• Authors: Bo Xiong, Mojtaba Nayyeri, Ming Jin, Yunjie He, Michael Cochez, Shirui Pan, Steffen Staab
• Abstract summary: We survey methods that underly geometric relational embeddings and categorize them based on the embedding geometries that are used to represent the data. We identify the desired properties (i.e., inductive biases) of each kind of embedding and discuss some potential future work.
• Score: 39.57716353191535
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Geometric relational embeddings map relational data as geometric objects that combine vector information suitable for machine learning and structured/relational information for structured/relational reasoning, typically in low dimensions. Their preservation of relational structures and their appealing properties and interpretability have led to their uptake for tasks such as knowledge graph completion, ontology and hierarchy reasoning, logical query answering, and hierarchical multi-label classification. We survey methods that underly geometric relational embeddings and categorize them based on (i) the embedding geometries that are used to represent the data; and (ii) the relational reasoning tasks that they aim to improve. We identify the desired properties (i.e., inductive biases) of each kind of embedding and discuss some potential future work.

Related papers

• Geometric Relational Embeddings [19.383110247906256]
  We propose relational embeddings, a paradigm of embeddings that respect the underlying symbolic structures. Results obtained from benchmark real-world datasets demonstrate the efficacy of geometric relational embeddings.
  arXiv  Detail & Related papers  (2024-09-18T22:02:24Z)
• Geometry of the Space of Partitioned Networks: A Unified Theoretical and Computational Framework [3.69102525133732]
  "Space of networks" has a complex structure that cannot be adequately described using conventional statistical tools. We introduce a measure-theoretic formalism for modeling generalized network structures such as graphs, hypergraphs, or graphs whose nodes come with a partition into categorical classes. We show that our metric is an Alexandrov space of non-negative curvature, and leverage this structure to define gradients for certain functionals commonly arising in geometric data analysis tasks.
  arXiv  Detail & Related papers  (2024-09-10T07:58:37Z)
• A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications [67.33002207179923]
  This paper presents a survey of data structures, models, and applications related to geometric GNNs. We provide a unified view of existing models from the geometric message passing perspective. We also summarize the applications as well as the related datasets to facilitate later research for methodology development and experimental evaluation.
  arXiv  Detail & Related papers  (2024-03-01T12:13:04Z)
• Learning Hierarchical Relational Representations through Relational Convolutions [2.5322020135765464]
  We introduce "relational convolutional networks", a neural architecture equipped with computational mechanisms that capture progressively more complex relational features. A key component of this framework is a novel operation that captures relational patterns in groups of objects by convolving graphlet filters. We present the motivation and details of the architecture, together with a set of experiments to demonstrate how relational convolutional networks can provide an effective framework for modeling relational tasks that have hierarchical structure.
  arXiv  Detail & Related papers  (2023-10-05T01:22:50Z)
• Towards a mathematical understanding of learning from few examples with nonlinear feature maps [68.8204255655161]
  We consider the problem of data classification where the training set consists of just a few data points. We reveal key relationships between the geometry of an AI model's feature space, the structure of the underlying data distributions, and the model's generalisation capabilities.
  arXiv  Detail & Related papers  (2022-11-07T14:52:58Z)
• On Neural Architecture Inductive Biases for Relational Tasks [76.18938462270503]
  We introduce a simple architecture based on similarity-distribution scores which we name Compositional Network generalization (CoRelNet) We find that simple architectural choices can outperform existing models in out-of-distribution generalizations.
  arXiv  Detail & Related papers  (2022-06-09T16:24:01Z)
• ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs [73.86041481470261]
  Cone Embeddings (ConE) is the first geometry-based query embedding model that can handle conjunction, disjunction, and negation. ConE significantly outperforms existing state-of-the-art methods on benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-26T14:04:02Z)
• Unraveling the graph structure of tabular datasets through Bayesian and spectral analysis [3.128267020893596]
  We show that the inference of the hierarchical modular structure obtained by the nested block model (nSBM) can help us identify the classes of features and unravel non-trivial relationships. We analyzed a socioeconomic survey conducted with students in Brazil: the PeNSE survey.
  arXiv  Detail & Related papers  (2021-10-04T12:51:55Z)
• pix2rule: End-to-end Neuro-symbolic Rule Learning [84.76439511271711]
  This paper presents a complete neuro-symbolic method for processing images into objects, learning relations and logical rules. The main contribution is a differentiable layer in a deep learning architecture from which symbolic relations and rules can be extracted. We demonstrate that our model scales beyond state-of-the-art symbolic learners and outperforms deep relational neural network architectures.
  arXiv  Detail & Related papers  (2021-06-14T15:19:06Z)
• Hermitian Symmetric Spaces for Graph Embeddings [0.0]
  We learn continuous representations of graphs in spaces of symmetric matrices over C. These spaces offer a rich geometry that simultaneously admits hyperbolic and Euclidean subspaces. The proposed models are able to automatically adapt to very dissimilar arrangements without any apriori estimates of graph features.
  arXiv  Detail & Related papers  (2021-05-11T18:14:52Z)

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.