Parameter-efficient Quantum Multi-task Learning

2026-04-15

AI Summary

This work addresses the challenge in multi-task learning where task-specific parameters grow rapidly with the number of tasks, compromising both model specificity and efficiency. To overcome this, the authors propose a parameter-efficient quantum multi-task learning framework that employs a shared quantum encoding layer followed by lightweight, task-specific variational quantum circuits (VQCs) as prediction heads—a novel application of VQCs in multi-task architectures. This design reduces the growth of prediction head parameters from quadratic to linear relative to the number of tasks. The approach matches or surpasses the performance of classical hard parameter-sharing models across three benchmarks: natural language processing, medical imaging, and multimodal sarcasm detection, while substantially reducing parameter count. Feasibility is further demonstrated on both noisy simulators and real quantum hardware.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Multi-modal Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Multi-task learning (MTL) improves generalization and data efficiency by jointly learning related tasks through shared representations. In the widely used hard-parameter-sharing setting, a shared backbone is combined with task-specific prediction heads. However, task-specific parameters can grow rapidly with the number of tasks. Therefore, designing multi-task heads that preserve task specialization while improving parameter efficiency remains a key challenge. In Quantum Machine Learning (QML), variational quantum circuits (VQCs) provide a compact mechanism for mapping classical data to quantum states residing in high-dimensional Hilbert spaces, enabling expressive representations within constrained parameter budgets. We propose a parameter-efficient quantum multi-task learning (QMTL) framework that replaces conventional task-specific linear heads with a fully quantum prediction head in a hybrid architecture. The model consists of a VQC with a shared, task-independent quantum encoding stage, followed by lightweight task-specific ansatz blocks enabling localized task adaptation while maintaining compact parameterization. Under a controlled and capacity-matched formulation where the shared representation dimension grows with the number of tasks, our parameter-scaling analysis demonstrates that a standard classical head exhibits quadratic growth, whereas the proposed quantum head parameter cost scales linearly. We evaluate QMTL on three multi-task benchmarks spanning natural language processing, medical imaging, and multimodal sarcasm detection, where we achieve performance comparable to, and in some cases exceeding, classical hard-parameter-sharing baselines while consistently outperforming existing hybrid quantum MTL models with substantially fewer head parameters. We further demonstrate QMTL's executability on noisy simulators and real quantum hardware, illustrating its feasibility.

Problem

• multi-task learning
• parameter efficiency
• task-specific heads
• hard-parameter-sharing
• quantum machine learning

Innovation

• quantum multi-task learning
• parameter efficiency
• variational quantum circuits
• quantum prediction head
• hard-parameter-sharing