Constraint Learning

Constraint learning focuses on automatically acquiring constraints from data, rather than relying on manual specification, to improve the efficiency and effectiveness of various tasks. Current research emphasizes learning both linear and nonlinear constraints using diverse methods, including graph neural networks for optimizing constraint generation, positive-unlabeled learning from demonstrations for inferring continuous constraints, and deep neural networks with tailored loss functions for direct constraint extraction. This field is significant because it enables automation in areas like robotic control, optimization problems, and machine learning model improvement, leading to more robust and efficient solutions in diverse applications.

Papers

November 12, 2024

Constraint Learning for Parametric Point Cloud
Xi Cheng, Ruiqi Lei, Di Huang, Zhichao Liao, Fengyuan Piao, Yan Chen, Pingfa Feng, Long Zeng
Point Cloud 3D Point Cloud Constraint Learning CAD Shape

September 10, 2024

Learn2Aggregate: Supervised Generation of Chvátal-Gomory Cuts Using Graph Neural Networks
Arnaud Deza, Elias B. Khalil, Zhenan Fan, Zirui Zhou, Yong Zhang
Graph Neural Network Cut and Approximate Constraint Learning Unsupervised Generation

August 3, 2024

Positive-Unlabeled Constraint Learning (PUCL) for Inferring Nonlinear Continuous Constraints Functions from Expert Demonstrations
Baiyu Peng, Aude Billard
Expert Demonstration Positive Unlabeled Learning Constraint Learning Unknown Constraint Nonlinear Constraint Accuracy Constraint

July 23, 2024

Learning General Continuous Constraint from Demonstrations via Positive-Unlabeled Learning
Baiyu Peng, Aude Billard
Noisy Demonstration Positive Unlabeled Learning Constraint Learning Hard Constraint Unknown Constraint Nonlinear Constraint Accuracy Constraint

March 13, 2024

Structural perspective on constraint-based learning of Markov networks
Tuukka Korhonen, Fedor V. Fomin, Pekka Parviainen
Markov Chain Probabilistic Graphical Model Structure Learning Constraint Learning Information Approach

March 4, 2024

Deep Neural Network for Constraint Acquisition through Tailored Loss Function
Eduardo Vyhmeister, Rocio Paez, Gabriel Gonzalez
Deep Neural Network Loss Function Symbolic Regression Participation Constraint Constraint Learning Constraint Acquisition

January 29, 2024

On the generalization of learned constraints for ASP solving in temporal domains
Javier Romero, Torsten Schaub, Klaus Strauch
Strong Generalization Participation Constraint Answer Set Programming Constraint Learning Temporal Domain Hard Inequality Constraint Operational Constraint

November 3, 2023

Global Optimization: A Machine Learning Approach
Dimitris Bertsimas, Georgios Margaritis
Robust Optimization Machine Learning Approach Mixed Integer Global Optimization Constraint Learning Global Optimization Problem

October 16, 2023

Time integration schemes based on neural networks for solving partial differential equations on coarse grids
Xinxin Yan, Zhideng Zhou, Xiaohan Cheng, Xiaolei Yang
Neural Network Partial Differential Equation Numerical Discretization Constraint Learning Coarse Grid Time Integration Scheme

September 1, 2023

Learning Shared Safety Constraints from Multi-task Demonstrations
Konwoo Kim, Gokul Swamy, Zuxin Liu, Ding Zhao, Sanjiban Choudhury, Zhiwei Steven Wu
High Dimensional Inverse Reinforcement Learning Safety Constraint Constraint Learning Conservative Constraint

July 28, 2023

Learning with Constraint Learning: New Perspective, Solution Strategy and Various Applications
Risheng Liu, Jiaxin Gao, Xuan Liu, Xin Fan
LeArning Abstract Generative Adversarial Network Financial Application New Perspective Constraint Learning Vision Application Computer Vision Problem Solution Approach

July 14, 2023

Structured Pruning of Neural Networks for Constraints Learning
Matteo Cacciola, Antonio Frangioni, Andrea Lodi
Neural Network Machine Learning Machine Learning Model Structured Pruning Machine Learning Application Constraint Learning Artificial Neural Network

June 21, 2023

Inverse Constraint Learning and Generalization by Transferable Reward Decomposition
Jaehwi Jang, Minjae Song, Daehyung Park
Strong Generalization Task Transferability Constraint Learning Policy Constraint rEward Decomposition Adaptivity Constraint

May 25, 2023

Learning Safety Constraints from Demonstrations with Unknown Rewards
David Lindner, Xin Chen, Sebastian Tschiatschek, Katja Hofmann, Andreas Krause
Reinforcement Learning Inverse Reinforcement Learning Noisy Demonstration Convex Set Constraint Learning

March 20, 2023

Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement
Michael Chang, Alyssa L. Dayan, Franziska Meier, Thomas L. Griffiths, Sergey Levine, Amy Zhang
Offline Reinforcement Learning Visual Input Object Rearrangement Constraint Learning Rearrangement Task Combinatorial Generalization Multilevel Abstraction

November 5, 2022

A Filtering-based General Approach to Learning Rational Constraints of Epistemic Graphs
Xiao Chi
Constraint Learning New Filtering Accuracy Constraint Probabilistic Argumentation Epistemic Graph

September 27, 2022

Semi-Blind Source Separation with Learned Constraints
Rémi Carloni Gertosio, Jérôme Bobin, Fabio Acero
Hyperspectral Image Source Separation Blind Source Separation Constraint Learning Semi Blind Source Separation

September 22, 2022

Counterfactual Explanations Using Optimization With Constraint Learning
Donato Maragno, Tabea E. Röber, Ilker Birbil
Optimization Purpose Counterfactual Explanation Constraint Learning

August 24, 2022

Constraint-driven multi-task learning
Bogdan Cretu, Andrew Cropper
Multi Task Learning Logic Program Inductive Logic Programming Constraint Learning Iterative Neural Network

June 15, 2022

Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization
Jivat Neet Kaur, Emre Kiciman, Amit Sharma
Distribution Generalization Data Generation Constraint Learning

Constraint Learning

Papers

Constraint Learning for Parametric Point Cloud

Learn2Aggregate: Supervised Generation of Chvátal-Gomory Cuts Using Graph Neural Networks

Positive-Unlabeled Constraint Learning (PUCL) for Inferring Nonlinear Continuous Constraints Functions from Expert Demonstrations

Learning General Continuous Constraint from Demonstrations via Positive-Unlabeled Learning

Structural perspective on constraint-based learning of Markov networks

Deep Neural Network for Constraint Acquisition through Tailored Loss Function

On the generalization of learned constraints for ASP solving in temporal domains

Global Optimization: A Machine Learning Approach

Time integration schemes based on neural networks for solving partial differential equations on coarse grids

Learning Shared Safety Constraints from Multi-task Demonstrations

Learning with Constraint Learning: New Perspective, Solution Strategy and Various Applications

Structured Pruning of Neural Networks for Constraints Learning

Inverse Constraint Learning and Generalization by Transferable Reward Decomposition

Learning Safety Constraints from Demonstrations with Unknown Rewards

Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement

A Filtering-based General Approach to Learning Rational Constraints of Epistemic Graphs

Semi-Blind Source Separation with Learned Constraints

Counterfactual Explanations Using Optimization With Constraint Learning

Constraint-driven multi-task learning

Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization