CoAction: Cross-task Correlation-aware Pareto Set Learning

2026-05-03

AI Summary

Existing Pareto set learning methods for multi-task multi-objective optimization typically model each task independently, failing to exploit inter-task correlations and incurring substantial computational overhead. To address this limitation, this work proposes CoAction, a novel framework that, for the first time, explicitly models task relationships within Pareto set learning. CoAction enables joint multi-task optimization and knowledge transfer through a task-aware Transformer architecture, employing task-specific embedding vectors in the encoder and leveraging self-attention mechanisms to capture complex inter-task dependencies. Experimental results demonstrate that CoAction consistently achieves significant improvements over existing approaches across multiple benchmarks and real-world scenarios, as measured by key performance indicators including hypervolume, spread, and sparsity.

Abstract

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.

Problem

• Pareto set learning
• multi-objective optimization
• multitask optimization
• cross-task correlation
• preference vector

Innovation

• Pareto set learning
• multi-objective multitask optimization
• task-aware transformer
• cross-task correlation
• self-attention mechanism