From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)

Abstract

This paper proposes a tentative and original survey of meeting points between Knowledge Representation and Reasoning (KRR) and Machine Learning (ML), two areas which have been developing quite separately in the last three decades. Some common concerns are identified and discussed such as the types of used representation, the roles of knowledge and data, the lack or the excess of information, or the need for explanations and causal understanding. Then some methodologies combining reasoning and learning are reviewed (such as inductive logic programming, neuro-symbolic reasoning, formal concept analysis, rule-based representations and ML, uncertainty in ML, or case-based reasoning and analogical reasoning), before discussing examples of synergies between KRR and ML (including topics such as belief functions on regression, EM algorithm versus revision, the semantic description of vector representations, the combination of deep learning with high level inference, knowledge graph completion, declarative frameworks for data mining, or preferences and recommendation). This paper is the first step of a work in progress aiming at a better mutual understanding of research in KRR and ML, and how they could cooperate.

53 pages

References in corpus (27)

• Explaining and Harnessing Adversarial Examples
• Methods for Interpreting and Understanding Deep Neural Networks
• CP-nets: A Tool for Representing and Reasoning withConditional Ceteris Paribus Preference Statements
• Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
• Neural Combinatorial Optimization with Reinforcement Learning
• Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
• Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI
• Metrics for Explainable AI: Challenges and Prospects
• The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
• Neuro-Symbolic Program Synthesis
• Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning
• Neural Logic Machines
• Deep Learning for Ontology Reasoning
• Holophrasm: a neural Automated Theorem Prover for higher-order logic
• Learning to Prove Theorems via Interacting with Proof Assistants
• VERIFAI: A Toolkit for the Design and Analysis of Artificial Intelligence-Based Systems
• Explaining Explanations to Society
• Deep Reasoning Networks: Thinking Fast and Slow
• Graph Neural Reasoning for 2-Quantified Boolean Formula Solvers
• Verification of Non-Linear Specifications for Neural Networks
• Building Robust Deep Neural Networks for Road Sign Detection
• PDP: A General Neural Framework for Learning Constraint Satisfaction Solvers
• Graph Neural Reasoning May Fail in Certifying Boolean Unsatisfiability
• Guiding High-Performance SAT Solvers with Unsat-Core Predictions
• Encoding Markov Logic Networks in Possibilistic Logic
• On Learning to Prove
• Stacked Structure Learning for Lifted Relational Neural Networks