Discriminative Gaifman Models

We present discriminative Gaifman models, a novel family of relational machine learning models. Gaifman models learn feature representations bottom up from representations of locally connected and bounded-size regions of knowledge bases (KBs). Considering local and bounded-size neighborhoods of knowledge bases renders logical inference and learning tractable, mitigates the problem of overfitting, and facilitates weight sharing. Gaifman models sample neighborhoods of knowledge bases so as to make the learned relational models more robust to missing objects and relations which is a common situation in open-world KBs. We present the core ideas of Gaifman models and apply them to large-scale relational learning problems. We also discuss the ways in which Gaifman models relate to some existing relational machine learning approaches.

• Publication year

  2016

• Venue

  Neural Information Processing Systems

• Publication date

  2016-10-01

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1610.09369
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Knowledge Graph Completion with Adaptive Sparse Transfer Matrix

  2016cited by this paper
• Complex Embeddings for Simple Link Prediction

  2016cited by this paper
• Efficient and Expressive Knowledge Base Completion Using Subgraph Feature Extraction

  2015cited by this paper
• Modeling Relation Paths for Representation Learning of Knowledge Bases

  2015cited by this paper
• A Review of Relational Machine Learning for Knowledge Graphs

  2015cited by this paper
• Injecting Logical Background Knowledge into Embeddings for Relation Extraction

  2015cited by this paper
• ProbLog2: Probabilistic Logic Programming

  2015cited by this paper
• Learning Entity and Relation Embeddings for Knowledge Graph Completion

  2015cited by this paper
• Embedding Entities and Relations for Learning and Inference in Knowledge Bases

  2014influential reference
• Lifted Inference and Learning in Statistical Relational Models

  2013cited by this paper
• Relation Extraction with Matrix Factorization and Universal Schemas

  2013influential reference
• YAGO2: A Spatially and Temporally Enhanced Knowledge Base from Wikipedia: Extended Abstract

  2013cited by this paper
• Reasoning With Neural Tensor Networks for Knowledge Base Completion

  2013cited by this paper
• Translating Embeddings for Modeling Multi-relational Data

  2013cited by this paper
• Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing

  2012cited by this paper
• Lifted Probabilistic Inference

  2012cited by this paper
• A latent factor model for highly multi-relational data

  2012influential reference
• A Three-Way Model for Collective Learning on Multi-Relational Data

  2011cited by this paper
• Learning Structured Embeddings of Knowledge Bases

  2011cited by this paper
• Random Walk Inference and Learning in A Large Scale Knowledge Base

  2011influential reference
• Global Learning of Typed Entailment Rules

  2011cited by this paper
• Toward an Architecture for Never-Ending Language Learning

  2010cited by this paper
• Learning First-Order Horn Clauses from Web Text

  2010cited by this paper
• Freebase: a collaboratively created graph database for structuring human knowledge

  2008cited by this paper
• Unsupervised Resolution of Objects and Relations on the Web

  2007cited by this paper
• Probabilistic models with unknown objects

  2006cited by this paper
• Probabilistic models with unknown objects

  2006cited by this paper
• Markov logic networks

  2006cited by this paper
• Elements of Finite Model Theory

  2004cited by this paper
• On Local and Non-Local Properties

  1982cited by this paper
• The complexity of relational query languages (Extended Abstract)

  1982cited by this paper

• Grounding Methods for Neural-Symbolic AI

  2025cites this paper
• Fast and Slow Thinking: A Two-Step Schema-Aware Approach for Instance Completion in Knowledge Graphs

  2024cites this paper
• HELIOS: Hyper-Relational Schema Modeling from Knowledge Graphs

  2023cites this paper
• Convolutional Models with Multi-Feature Fusion for Effective Link Prediction in Knowledge Graph Embedding

  2023cites this paper
• KGRACDA: A Model Based on Knowledge Graph from Recursion and Attention Aggregation for CircRNA-disease Association Prediction

  2023influential citation
• A Statistical Relational Approach to Learning Distance-based GCNs

  2021cites this paper
• Knowledge Graph Reasoning with Relational Directed Graph

  2021cites this paper
• RETA: A Schema-Aware, End-to-End Solution for Instance Completion in Knowledge Graphs

  2021cites this paper
• Learning Representations for Sub-Symbolic Reasoning

  2021cites this paper
• Bridging Graph Neural Networks and Statistical Relational Learning: Relational One-Class GCN

  2021cites this paper
• Relational reasoning networks

  2021cites this paper
• Knowledge Graph Reasoning with Relational Digraph

  2021cites this paper
• Non-parametric Learning of Embeddings for Relational Data Using Gaifman Locality Theorem

  2021influential citation
• Knowledge Base Population via Relational One-Class Graph Convolutional Networks

  2020cites this paper
• Relational Neural Machines

  2020cites this paper
• Non-Parametric Learning of Gaifman Models

  2020influential citation
• Inference in relational neural machines

  2020cites this paper
• Semantic Relations and Deep Learning

  2020influential citation
• A survey of embedding models of entities and relationships for knowledge graph completion

  2020cites this paper
• Knowledge Base Population via Relational One-Class Graph Convolutional Networks

  2020influential citation
• DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs

  2019cites this paper
• LENA: Locality-Expanded Neural Embedding for Knowledge Base Completion

  2019cites this paper
• Adaptive Convolution for Multi-Relational Learning

  2019cites this paper
• Anytime Bottom-Up Rule Learning for Knowledge Graph Completion

  2019cites this paper
• Representing and learning relations and properties under uncertainty

  2018cites this paper
• Automatic refinement of large-scale cross-domain knowledge graphs

  2018cites this paper
• From Knowledge Graph Embedding to Ontology Embedding? An Analysis of the Compatibility between Vector Space Representations and Rules

  2018cites this paper
• Fine-Grained Evaluation of Rule- and Embedding-Based Systems for Knowledge Graph Completion

  2018cites this paper
• Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures

  2018cites this paper
• SimplE Embedding for Link Prediction in Knowledge Graphs

  2018cites this paper
• Regularizing Knowledge Graph Embeddings via Equivalence and Inversion Axioms

  2017cites this paper
• Adversarial Sets for Regularising Neural Link Predictors

  2017cites this paper
• Complex-Valued Embedding Models for Knowledge Graphs

  2017cites this paper
• Convolutional 2D Knowledge Graph Embeddings

  2017cites this paper
• KBlrn: End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features

  2017cites this paper
• Knowledge Graph Completion via Complex Tensor Factorization

  2017cites this paper
• On Multi-Relational Link Prediction with Bilinear Models

  2017cites this paper
• An overview of embedding models of entities and relationships for knowledge base completion

  2017cites this paper
• Knowledge Base Completion: Baselines Strike Back

  2017cites this paper
• Clustering-Based Relational Unsupervised Representation Learning with an Explicit Distributed Representation

  2016cites this paper
• STransE: a novel embedding model of entities and relationships in knowledge bases

  2016cites this paper
• Neighborhood Mixture Model for Knowledge Base Completion

  2016cites this paper
• Book Reviews: Semantic Relations Between Nominals by Vivi Nastase, Preslav Nakov, Diarmuid Ó Séaghdha, and Stan Szpakowicz

  2013influential citation