UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Adversarial Sets for Regularising Neural Link Predictors

Minervini, P; Demeester, T; Rocktäschel, T; Riedel, S; (2017) Adversarial Sets for Regularising Neural Link Predictors. In: Elidan, Gal and Kersting, Kristian and Ihler, Alexander, (eds.) Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence (UAI 2017). Curran Associates Inc: Red Hook, NY, USA. Green open access

[thumbnail of uai17.pdf]
Preview
Text
uai17.pdf - Accepted Version

Download (426kB) | Preview

Abstract

In adversarial training, a set of models learn together by pursuing competing goals, usually defined on single data instances. However, in relational learning and other non-i.i.d domains, goals can also be defined over sets of instances. For example, a link predictor for the IS-A relation needs to be consistent with the transitivity property: if IS-A(x1; x2) and IS-A(x2; x3) hold, IS-A(x1; x3) needs to hold as well. Here we use such assumptions for deriving an inconsistency loss, measuring the degree to which the model violates the assumptions on an adversarially-generated set of examples. The training objective is defined as a minimax problem, where an adversary finds the most offending adversarial examples by maximising the inconsistency loss, and the model is trained by jointly minimising a supervised loss and the inconsistency loss on the adversarial examples. This yields the first method that can use function-free Horn clauses (as in Datalog) to regularise any neural link predictor, with complexity independent of the domain size. We show that for several link prediction models, the optimisation problem faced by the adversary has efficient closedform solutions. Experiments on link prediction benchmarks indicate that given suitable prior knowledge, our method can significantly improve neural link predictors on all relevant metrics.

Type: Proceedings paper
Title: Adversarial Sets for Regularising Neural Link Predictors
Event: 33rd Conference on Uncertainty in Artificial Intelligence (UAI), 11-15 August 2017, Sydney, Australia
ISBN-13: 9781510847798
Open access status: An open access version is available from UCL Discovery
Publisher version: http://www.auai.org/uai2017/accepted.php
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/10043030
Downloads since deposit
22Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item