Saved in:
Bibliographic Details
Main Authors: Chen, Xinyue, Liang, Yingxuan, Huang, Yiqin, Shang, Chikai, Liu, Hai-Lin, Gu, Fangqing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.01712
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909011303989248
author Chen, Xinyue
Liang, Yingxuan
Huang, Yiqin
Shang, Chikai
Liu, Hai-Lin
Gu, Fangqing
author_facet Chen, Xinyue
Liang, Yingxuan
Huang, Yiqin
Shang, Chikai
Liu, Hai-Lin
Gu, Fangqing
contents Pareto set learning (PSL) is an emerging paradigm in multi-objective optimization that trains neural networks to map preference vectors to Pareto optimal solutions. However, existing PSL methods primarily focus on solving a single multi-objective optimization problem at a time. This limitation not only increases computational costs in multi-objective multitask optimization scenarios by requiring a separate model for each task, but also fails to exploit the inter-task correlations across tasks. To address this, we propose a Cross-tAsk correlation-aware Pareto Set Learning (CoAction) framework, which leverages task-aware transformer to handle multiple tasks simultaneously. Specifically, by assigning task-specific embedding vectors to individual tasks, the model effectively distinguishes between tasks while facilitating knowledge sharing among them. We utilize a Transformer encoder as the backbone architecture to leverage its self-attention mechanism for capturing complex task dependencies. The proposed approach is evaluated on comprehensive multitask test suites covering both benchmark problems and real-world applications, demonstrating effectiveness and competitive performance in Hypervolume, Range, and Sparsity.
format Preprint
id arxiv_https___arxiv_org_abs_2605_01712
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CoAction: Cross-task Correlation-aware Pareto Set Learning
Chen, Xinyue
Liang, Yingxuan
Huang, Yiqin
Shang, Chikai
Liu, Hai-Lin
Gu, Fangqing
Machine Learning
Pareto set learning (PSL) is an emerging paradigm in multi-objective optimization that trains neural networks to map preference vectors to Pareto optimal solutions. However, existing PSL methods primarily focus on solving a single multi-objective optimization problem at a time. This limitation not only increases computational costs in multi-objective multitask optimization scenarios by requiring a separate model for each task, but also fails to exploit the inter-task correlations across tasks. To address this, we propose a Cross-tAsk correlation-aware Pareto Set Learning (CoAction) framework, which leverages task-aware transformer to handle multiple tasks simultaneously. Specifically, by assigning task-specific embedding vectors to individual tasks, the model effectively distinguishes between tasks while facilitating knowledge sharing among them. We utilize a Transformer encoder as the backbone architecture to leverage its self-attention mechanism for capturing complex task dependencies. The proposed approach is evaluated on comprehensive multitask test suites covering both benchmark problems and real-world applications, demonstrating effectiveness and competitive performance in Hypervolume, Range, and Sparsity.
title CoAction: Cross-task Correlation-aware Pareto Set Learning
topic Machine Learning
url https://arxiv.org/abs/2605.01712