Multi-Task Optimization over Networks of Tasks

2026-04-23

AI Summary

This work addresses the challenge that existing large-scale multitask optimization methods struggle to simultaneously achieve scalability and effective exploitation of inter-task topological structures when the number of tasks scales to thousands. To overcome this limitation, the authors propose MONET, an algorithm that explicitly models the task space as a graph network for the first time, integrating social learning (crossover) between nodes with individual learning (mutation) within nodes to enable efficient knowledge transfer. By preserving strong scalability while effectively leveraging task topology, MONET matches or surpasses state-of-the-art MAP-Elites-based baselines across four high-dimensional task domains, each comprising 2,000 to 5,000 tasks.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Economics, Online Markets and Human Computation: Social networks and social learning
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Multi-task optimization is a powerful approach for solving a large number of tasks in parallel. However, existing algorithms face distinct limitations: Population-based methods scale poorly and remain underexplored for large task sets. Approaches that do scale beyond a thousand tasks are mostly MAP-Elites variants and rely on a fixed, discretized archive that disregards the topology of the task space. We introduce MONET (Multi-Task Optimization over Networks of Tasks), a multi-task optimization algorithm that models the task space as a graph: tasks are nodes, and edges connect tasks in the task parameter space. This representation enables knowledge transfer between tasks and remains tractable for high-dimensional problems while exploiting the topology of the task space. MONET combines social learning, which generates candidates from neighboring nodes via crossover, with individual learning, which refines a node's own solution independently via mutation. We evaluate MONET on four domains (archery, arm, and cartpole with 5,000 tasks each; hexapod with 2,000 tasks) and show that it matches or exceeds the performance of existing MAP-Elites-based baselines across all four domains.

Problem

• multi-task optimization
• task space topology
• scalability
• knowledge transfer
• MAP-Elites

Innovation

• multi-task optimization
• task space topology
• graph-based representation
• social learning
• knowledge transfer