A Hyper-Transformer model for Controllable Pareto Front Learning with Split Feasibility Constraints

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tuan, Tran Anh, Dung, Nguyen Viet, Thang, Tran Ngoc
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916118740860928
author Tuan, Tran Anh
Dung, Nguyen Viet
Thang, Tran Ngoc
author_facet Tuan, Tran Anh
Dung, Nguyen Viet
Thang, Tran Ngoc
contents Controllable Pareto front learning (CPFL) approximates the Pareto solution set and then locates a Pareto optimal solution with respect to a given reference vector. However, decision-maker objectives were limited to a constraint region in practice, so instead of training on the entire decision space, we only trained on the constraint region. Controllable Pareto front learning with Split Feasibility Constraints (SFC) is a way to find the best Pareto solutions to a split multi-objective optimization problem that meets certain constraints. In the previous study, CPFL used a Hypernetwork model comprising multi-layer perceptron (Hyper-MLP) blocks. With the substantial advancement of transformer architecture in deep learning, transformers can outperform other architectures in various tasks. Therefore, we have developed a hyper-transformer (Hyper-Trans) model for CPFL with SFC. We use the theory of universal approximation for the sequence-to-sequence function to show that the Hyper-Trans model makes MED errors smaller in computational experiments than the Hyper-MLP model.
format Preprint
id arxiv_https___arxiv_org_abs_2402_05955
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Hyper-Transformer model for Controllable Pareto Front Learning with Split Feasibility Constraints
Tuan, Tran Anh
Dung, Nguyen Viet
Thang, Tran Ngoc
Machine Learning
Optimization and Control
Controllable Pareto front learning (CPFL) approximates the Pareto solution set and then locates a Pareto optimal solution with respect to a given reference vector. However, decision-maker objectives were limited to a constraint region in practice, so instead of training on the entire decision space, we only trained on the constraint region. Controllable Pareto front learning with Split Feasibility Constraints (SFC) is a way to find the best Pareto solutions to a split multi-objective optimization problem that meets certain constraints. In the previous study, CPFL used a Hypernetwork model comprising multi-layer perceptron (Hyper-MLP) blocks. With the substantial advancement of transformer architecture in deep learning, transformers can outperform other architectures in various tasks. Therefore, we have developed a hyper-transformer (Hyper-Trans) model for CPFL with SFC. We use the theory of universal approximation for the sequence-to-sequence function to show that the Hyper-Trans model makes MED errors smaller in computational experiments than the Hyper-MLP model.
title A Hyper-Transformer model for Controllable Pareto Front Learning with Split Feasibility Constraints
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2402.05955