From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
arXiv:1912.06612
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 (61)
- Explaining and Harnessing Adversarial Examples
- Neural Message Passing for Quantum Chemistry
- Methods for Interpreting and Understanding Deep Neural Networks
- Binarized Neural Networks
- ParamILS: An Automatic Algorithm Configuration Framework
- CP-nets: A Tool for Representing and Reasoning withConditional Ceteris Paribus Preference Statements
- SATzilla: Portfolio-based Algorithm Selection for SAT
- Explaining Explanations in AI
- A tutorial on conformal prediction
- Adversarial Attacks and Defences: A Survey
- SimplE Embedding for Link Prediction in Knowledge Graphs
- Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search
- Wasserstein Distance Guided Representation Learning for Domain Adaptation
- 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 Power of Depth for Feedforward Neural Networks
- Learning Deep Features for Discriminative Localization
- Differentiable Learning of Logical Rules for Knowledge Base Reasoning
- Learning-Assisted Automated Reasoning with Flyspeck
- Logistic Regression, Neural Networks and Dempster-Shafer Theory: a New Perspective
- The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
- A Unified View of Piecewise Linear Neural Network Verification
- End-to-End Differentiable Proving
- SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions
- DeepMath - Deep Sequence Models for Premise Selection
- Neuro-Symbolic Program Synthesis
- Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning
- Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples
- Automated Verification of Neural Networks: Advances, Challenges and Perspectives
- Neural Logic Machines
- Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis
- Branch and Bound for Piecewise Linear Neural Network Verification
- Reachability Analysis of Deep Neural Networks with Provable Guarantees
- Deep Learning for Ontology Reasoning
- Holophrasm: a neural Automated Theorem Prover for higher-order logic
- Learning to Prove Theorems via Interacting with Proof Assistants
- From Knowledge Graph Embedding to Ontology Embedding? An Analysis of the Compatibility between Vector Space Representations and Rules
- Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values
- Towards Neural Theorem Proving at Scale
- Neural Guided Constraint Logic Programming for Program Synthesis
- Recurrent Relational Networks
- Reinforcement Learning of Theorem Proving
- Tunneling Neural Perception and Logic Reasoning through Abductive Learning
- VERIFAI: A Toolkit for the Design and Analysis of Artificial Intelligence-Based Systems
- Explaining Explanations to Society
- Verification of deep probabilistic models
- Deep Reasoning Networks: Thinking Fast and Slow
- Graph Neural Reasoning for 2-Quantified Boolean Formula Solvers
- Building Robust Deep Neural Networks for Road Sign Detection
- Verification of Non-Linear Specifications for Neural Networks
- PDP: A General Neural Framework for Learning Constraint Satisfaction Solvers
- Graph Neural Reasoning May Fail in Certifying Boolean Unsatisfiability
- ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks
- Guiding High-Performance SAT Solvers with Unsat-Core Predictions
- Encoding Markov Logic Networks in Possibilistic Logic
- On Learning to Prove
- Universal Approximation with Certified Networks
- Stacked Structure Learning for Lifted Relational Neural Networks