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.

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.

Download activity - last month

Export as CSVXMLJSON

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item