Rule Discovery

Rule discovery focuses on automatically extracting meaningful "if-then" rules from data, aiming to improve model interpretability and facilitate decision-making in various domains. Current research emphasizes developing algorithms that efficiently discover accurate and concise rules, often employing techniques like clustering analysis, temporal point processes, and reinforcement learning within frameworks such as boosting and knowledge distillation. These advancements are impacting fields ranging from healthcare (diagnosing unusual events) to e-commerce (predicting product compatibility) by providing explainable models and actionable insights from complex datasets. The resulting interpretable rules enhance trust in AI systems and enable more effective data analysis.

Papers

February 9, 2024

A Methodology for Questionnaire Analysis: Insights through Cluster Analysis of an Investor Competition Data
Carlos Henrique Q. Forster, Paulo André Lima de Castro, Andrei Ramalho
NCD Method DCU Insight AQ Cluster Analysis Question Classification Standardized Questionnaire Rule Discovery

February 3, 2024

Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation
Yiling Kuang, Chao Yang, Yang Yang, Shuang Li
Causal Direction Temporal Point Process Latent Causal Anomalous Data Rule Discovery

January 31, 2024

SDRDPy: An application to graphically visualize the knowledge obtained with supervised descriptive rule algorithms
M. A. Padilla-Rascon, P. Gonzalez, C. J. Carmona
Application Proficiency General Analysis Knowledge Based Simple RULE Rule Discovery Expert Observation

January 26, 2024

Extracting Process-Aware Decision Models from Object-Centric Process Data
Alexandre Goossens, Johannes De Smedt, Jan Vanthienen
Object Centric Decision Making Algorithm Rule Discovery Decision Making Model

November 24, 2023

Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery
Ekaterina Nikonova, Cheng Xue, Jochen Renz
Deep Reinforcement Learning Knowledge Distillation AI Agent Open World Deep Reinforcement Deep Q Rule Discovery

July 12, 2022

Investigating the Impact of Independent Rule Fitnesses in a Learning Classifier System
Michael Heider, Helena Stegherr, Jonathan Wurth, Roman Sraj, Jörg Hähner
Global Impact High Explainability Rule Based Fitness Function Learning Classifier Rule Discovery

June 28, 2022

Adaptive Multi-view Rule Discovery for Weakly-Supervised Compatible Products Prediction
Rongzhi Zhang, Rebecca West, Xiquan Cui, Chao Zhang
Pseudo Label Multi View Learning Structured Product Rule Discovery Cross Domain Product

May 13, 2022

R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning
Shengyao Lu, Bang Liu, Keith G. Mills, Shangling Jui, Di Niu
Relational Reasoning Relation Prediction Rule Discovery Relation Prediction Task

March 18, 2022

PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning
Rongzhi Zhang, Yue Yu, Pranav Shetty, Le Song, Chao Zhang
LeArning Abstract Pseudo Label Weakly Supervised Weakly Supervised Learning Interactive No Code Token Boosting Weak Label Labeling Technique Rule Discovery

February 3, 2022

Separating Rule Discovery and Global Solution Composition in a Learning Classifier System
Michael Heider, Helena Stegherr, Jonathan Wurth, Roman Sraj, Jörg Hähner
Line by Line Explanation High Explainability Rule Based Fitness Function Learning Classifier Rule Discovery Global Solution

December 9, 2021

A Novel Tropical Geometry-based Interpretable Machine Learning Method: Application in Prognosis of Advanced Heart Failure
Heming Yao, Harm Derksen, Jessica R. Golbus, Justin Zhang, Keith D. Aaronson, Jonathan Gryak, Kayvan Najarian
Application Proficiency Inherent Interpretability Prognosis Prediction Heart Failure Fuzzy Inference Interpretable Machine Learning Method Uncertain Domain Rule Discovery

November 4, 2021

Identifying the Leading Factors of Significant Weight Gains Using a New Rule Discovery Method
Mina Samizadeh, Jessica C Jones-Smith, Bethany Sheridan, Rahmatollah Beheshti
Key Factor Predictive Performance Big Gain Subgroup Discovery Distinct Pattern Rule Discovery

Rule Discovery

Papers

A Methodology for Questionnaire Analysis: Insights through Cluster Analysis of an Investor Competition Data

Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation

SDRDPy: An application to graphically visualize the knowledge obtained with supervised descriptive rule algorithms

Extracting Process-Aware Decision Models from Object-Centric Process Data

Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery

Investigating the Impact of Independent Rule Fitnesses in a Learning Classifier System

Adaptive Multi-view Rule Discovery for Weakly-Supervised Compatible Products Prediction

R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning

PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning

Separating Rule Discovery and Global Solution Composition in a Learning Classifier System

A Novel Tropical Geometry-based Interpretable Machine Learning Method: Application in Prognosis of Advanced Heart Failure

Identifying the Leading Factors of Significant Weight Gains Using a New Rule Discovery Method