Logistic Tensor Factorization for Multi-Relational Data

Abstract

Tensor factorizations have become increasingly popular approaches for various learning tasks on structured data. In this work, we extend the RESCAL tensor factorization, which has shown state-of-the-art results for multi-relational learning, to account for the binary nature of adjacency tensors. We study the improvements that can be gained via this approach on various benchmark datasets and show that the logistic extension can improve the prediction results significantly.

Accepted at ICML 2013 Workshop "Structured Learning: Inferring Graphs from Structured and Unstructured Inputs" (SLG 2013)

References in corpus (1)

• Multi-relational Learning Using Weighted Tensor Decomposition with Modular Loss

Cited by in corpus (8)

• A Review of Relational Machine Learning for Knowledge Graphs
• Generalized Canonical Polyadic Tensor Decomposition
• A generalizable framework for low-rank tensor completion with numerical priors
• Revisiting Simple Neural Networks for Learning Representations of Knowledge Graphs
• Binarized Canonical Polyadic Decomposition for Knowledge Graph Completion
• Compact Factorization of Matrices Using Generalized Round-Rank
• Binarized Knowledge Graph Embeddings
• A Probit Tensor Factorization Model For Relational Learning