Search papers, labs, and topics across Lattice.
This paper introduces a parameter-efficient quantum multi-task learning (QMTL) framework that replaces classical task-specific linear heads with a fully quantum prediction head in a hybrid architecture. The QMTL model uses a shared, task-independent quantum encoding stage followed by lightweight task-specific ansatz blocks, enabling localized task adaptation with fewer parameters. Experiments on NLP, medical imaging, and multimodal sarcasm detection benchmarks show QMTL achieves comparable or superior performance to classical baselines and outperforms existing hybrid quantum MTL models, while scaling linearly in parameter cost compared to the quadratic scaling of classical heads.
Quantum multi-task learning slashes parameter counts while matching or exceeding classical performance, offering a path to efficient learning across diverse tasks.
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.
