Rocktäschel, T;
Riedel, S;
(2017)
End-to-end differentiable proving.
In: Guyon, Isabelle and von Luxburg, Ulrike, (eds.)
NIPS'17 Proceedings of the 31st International Conference on Neural Information Processing Systems.
(pp. pp. 3791-3803).
ACM (Association for Computing Machinery): New York, USA.
Preview |
Text
Rocktäschel_AAM_1705.11040v2.pdf - Accepted Version Download (563kB) | Preview |
Abstract
We introduce deep neural networks for end-to-end differentiable theorem proving that operate on dense vector representations of symbols. These neural networks are recursively constructed by following the backward chaining algorithm as used in Prolog. Specifically, we replace symbolic unification with a differentiable computation on vector representations of symbols using a radial basis function kernel, thereby combining symbolic reasoning with learning subsymbolic vector representations. The resulting neural network can be trained to infer facts from a given incomplete knowledge base using gradient descent. By doing so, it learns to (i) place representations of similar symbols in close proximity in a vector space, (ii) make use of such similarities to prove facts, (iii) induce logical rules, and (iv) it can use provided and induced logical rules for complex multi-hop reasoning. On four benchmark knowledge bases we demonstrate that this architecture outperforms ComplEx, a state-of-the-art neural link prediction model, while at the same time inducing interpretable function-free first-order logic rules.
| Type: | Proceedings paper |
|---|---|
| Title: | End-to-end differentiable proving |
| Event: | 31st Conference on Neural Information Processing Systems (NIPS 2017), 4-9 December 2017, Long Beach, CA, USA |
| ISBN-13: | 978-1-5108-6096-4 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://dl.acm.org/citation.cfm?id=3295136 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10057152 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
