Complex Query Answering with Neural Link Predictors

by   Erik Arakelyan, et al.

Neural link predictors are immensely useful for identifying missing edges in large scale Knowledge Graphs. However, it is still not clear how to use these models for answering more complex queries that arise in a number of domains, such as queries using logical conjunctions (), disjunctions () and existential quantifiers (∃), while accounting for missing edges. In this work, we propose a framework for efficiently answering complex queries on incomplete Knowledge Graphs. We translate each query into an end-to-end differentiable objective, where the truth value of each atom is computed by a pre-trained neural link predictor. We then analyse two solutions to the optimisation problem, including gradient-based and combinatorial search. In our experiments, the proposed approach produces more accurate results than state-of-the-art methods – black-box neural models trained on millions of generated queries – without the need of training on a large and diverse set of complex queries. Using orders of magnitude less training data, we obtain relative improvements ranging from 8 knowledge graphs containing factual information. Finally, we demonstrate that it is possible to explain the outcome of our model in terms of the intermediate solutions identified for each of the complex query atoms.


page 1

page 2

page 3

page 4


Adapting Neural Link Predictors for Complex Query Answering

Answering complex queries on incomplete knowledge graphs is a challengin...

Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization

Answering complex logical queries on incomplete knowledge graphs is a ch...

Fuzzy Logic based Logical Query Answering on Knowledge Graph

Answering complex First-Order Logical (FOL) queries on large-scale incom...

Answering Complex Queries in Knowledge Graphs with Bidirectional Sequence Encoders

Representation learning for knowledge graphs (KGs) has focused on the pr...

How and Why is An Answer (Still) Correct? Maintaining Provenance in Dynamic Knowledge Graphs

Knowledge graphs (KGs) have increasingly become the backbone of many cri...

Logic Embeddings for Complex Query Answering

Answering logical queries over incomplete knowledge bases is challenging...

Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs

Complex Query Answering (CQA) is an important reasoning task on knowledg...

Please sign up or login with your details

Forgot password? Click here to reset