Logistic Tensor Factorization for Multi-Relational Data
This work addresses multi-relational data analysis, but it is incremental as it builds on an existing state-of-the-art method.
The authors tackled the problem of multi-relational learning by extending RESCAL tensor factorization to handle binary adjacency tensors, showing that this logistic extension significantly improves prediction results on benchmark datasets.
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.