This paper introduces a novel approach to relational learning using a three-way tensor factorization, named RESCAL. Unlike other tensor methods, RESCAL is designed to perform collective learning by leveraging the latent components of the model. The authors provide an efficient algorithm for computing the tensor factorization and demonstrate its effectiveness through experiments on both a new dataset and a commonly used entity resolution dataset. RESCAL outperforms or matches the performance of state-of-the-art relational learning solutions while being significantly faster to compute. The paper also discusses the theoretical foundations of RESCAL, its connections to other tensor factorizations, and its application to various relational learning tasks such as link prediction, collective classification, and entity resolution. The evaluation section shows that RESCAL achieves better or comparable results compared to existing methods, highlighting its potential as a promising approach in the field of relational learning.This paper introduces a novel approach to relational learning using a three-way tensor factorization, named RESCAL. Unlike other tensor methods, RESCAL is designed to perform collective learning by leveraging the latent components of the model. The authors provide an efficient algorithm for computing the tensor factorization and demonstrate its effectiveness through experiments on both a new dataset and a commonly used entity resolution dataset. RESCAL outperforms or matches the performance of state-of-the-art relational learning solutions while being significantly faster to compute. The paper also discusses the theoretical foundations of RESCAL, its connections to other tensor factorizations, and its application to various relational learning tasks such as link prediction, collective classification, and entity resolution. The evaluation section shows that RESCAL achieves better or comparable results compared to existing methods, highlighting its potential as a promising approach in the field of relational learning.