Timezone: »
Tensor factorizations have become popular methods for learning from multi-relational data. In this context, the rank of a factorization is an important parameter that determines runtime as well as generalization ability. To determine conditions under which factorization is an efficient approach for learning from relational data, we derive upper and lower bounds on the rank required to recover adjacency tensors. Based on our findings, we propose a novel additive tensor factorization model for learning from latent and observable patterns in multi-relational data and present a scalable algorithm for computing the factorization. Experimentally, we show that the proposed approach does not only improve the predictive performance over pure latent variable methods but that it also reduces the required rank --- and therefore runtime and memory complexity --- significantly.
Author Information
Maximilian Nickel (Facebook AI Research)
Xueyan Jiang (Ludwig-Maximilians-Universität München)
Volker Tresp (Siemens AG)
Related Events (a corresponding poster, oral, or spotlight)
-
2014 Spotlight: Reducing the Rank in Relational Factorization Models by Including Observable Patterns »
Wed Dec 10th 08:30 -- 08:50 PM Room Level 2, room 210
More from the Same Authors
-
2020 Workshop: Differential Geometry meets Deep Learning (DiffGeo4DL) »
Joey Bose · Emile Mathieu · Charline Le Lan · Ines Chami · Frederic Sala · Christopher De Sa · Maximillian Nickel · Christopher Ré · Will Hamilton -
2020 Poster: Riemannian Continuous Normalizing Flows »
Emile Mathieu · Maximilian Nickel -
2019 Poster: Hyperbolic Graph Neural Networks »
Qi Liu · Maximilian Nickel · Douwe Kiela -
2017 Poster: Poincaré Embeddings for Learning Hierarchical Representations »
Maximillian Nickel · Douwe Kiela -
2017 Spotlight: Poincaré Embeddings for Learning Hierarchical Representations »
Maximillian Nickel · Douwe Kiela -
2016 Workshop: Learning with Tensors: Why Now and How? »
Anima Anandkumar · Rong Ge · Yan Liu · Maximilian Nickel · Qi (Rose) Yu -
2015 Symposium: Brains, Minds and Machines »
Gabriel Kreiman · Tomaso Poggio · Maximilian Nickel -
2006 Poster: Gaussian Process Models for Discriminative Link Prediction »
Kai Yu · Wei Chu · Shipeng Yu · Volker Tresp · Zhao Xu