Adversarial Sets for Regularising Neural Link Predictors

07/24/2017
by   Pasquale Minervini, et al.
0

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(x_1, x_2) and is-a(x_2, x_3) hold, is-a(x_1, x_3) 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 closed-form solutions. Experiments on link prediction benchmarks indicate that given suitable prior knowledge, our method can significantly improve neural link predictors on all relevant metrics.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/16/2018

Embedding Cardinality Constraints in Neural Link Predictors

Neural link predictors learn distributed representations of entities and...
research
12/22/2020

Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction

Developing link prediction models to automatically complete knowledge gr...
research
08/14/2022

Link-Backdoor: Backdoor Attack on Link Prediction via Node Injection

Link prediction, inferring the undiscovered or potential links of the gr...
research
12/06/2021

Pairwise Learning for Neural Link Prediction

In this paper, we aim at providing an effective Pairwise Learning Neural...
research
06/13/2023

On Achieving Optimal Adversarial Test Error

We first elucidate various fundamental properties of optimal adversarial...
research
04/19/2022

RNNCTPs: A Neural Symbolic Reasoning Method Using Dynamic Knowledge Partitioning Technology

Although traditional symbolic reasoning methods are highly interpretable...
research
03/14/2022

Neural Theorem Provers Delineating Search Area Using RNN

Although traditional symbolic reasoning methods are highly interpretable...

Please sign up or login with your details

Forgot password? Click here to reset