Although deep reinforcement learning has become a promising machine learning approach
for sequential decision-making problems, it is still not mature enough for high-stake domains …

Large language models (LLMs) have revolutionized many areas (eg natural language
processing, software engineering, etc.) by achieving state-of-the-art performance on …

Learning logical rules is critical to improving reasoning in KGs. This is due to their ability to
provide logical and interpretable explanations when used for predictions, as well as their …

Rule-based models, eg, decision trees, are widely used in scenarios demanding high model
interpretability for their transparent inner structures and good model expressivity. However …

The goal of the growing discipline of neuro-symbolic artificial intelligence (AI) is to develop
AI systems with more human-like reasoning capabilities by combining symbolic reasoning …

The integration of reasoning, learning, and decision-making is key to build more general
artificial intelligence systems. As a step in this direction, we propose a novel neural-logic …

The proliferation of fake news has emerged as a severe societal problem, raising significant
interest from industry and academia. While existing deep-learning based methods have …

The goal of inductive logic programming is to induce a logic program (a set of logical rules)
that generalises training examples. Inducing programs with many rules and literals is a …

Though neural networks have achieved impressive prediction performance, it's still hard for
people to understand what neural networks have learned from the data. The black-box …

The ability to generalise from a small number of examples is a fundamental challenge in
machine learning. To tackle this challenge, we introduce an inductive logic programming …