Parameter-efficient Quantum Multi-task Learning

Hevish Cowlessur; Chandra Thapa; Tansu Alpcan; Seyit Camtepe

cs.LGApr 15, 2026

Parameter-efficient Quantum Multi-task Learning

Authors: Hevish Cowlessur, Chandra Thapa, Tansu Alpcan, Seyit Camtepe

Organizations: Department of Electrical and Electronic Engineering, University of Melbourne, Parkville, 3010, VIC, Australia. · CSIRO, Sydney, NSW, Australia.

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.

Figures & tables

Figure 1: Proposed Quantum Circuit architecture for multi-task learning. An extracted feature vector Z is embedded into a

Q

-qubit register via a shared trainable state-preparation stage

f_{Q}(\mathbf{Z},\mathbf{\Theta})

. This embeds Z to a quantum state

|\psi_{\Theta}(\mathbf{Z})\rangle

in superposition over computational basis states (a vector in a

2^{Q}

-dimensional complex Hilbert space). The register is then partitioned into

T

disjoint qubit sub-registers,

\mathcal{Q}_{t}\subseteq\{q_{0},\dots,q_{Q-1}\}

, and task-specific parameterized blocks

\{f_{\mathcal{Q}_{t}}\}_{t=1}^{T}

are applied on each sub-register to produce

T

measurement outcomes

\{\mathbf{\hat{y}_{t}\}}^{T}_{t=1}

within one circuit execution. This enables parameter-efficient MTL by sharing a common trainable backbone while allowing task specialization through localized operations and readouts.

Figure 2: Total number of trainable parameters in our proposed architecture (shown in Fig. 1 ) compared against the simplest classical counterpart. We assume that the output dimension of each task is

r

to aid analysis in this section.

Panel of Figure 3 — Figure 3: High-level overview of the experimental pipeline: Dataset $\rightarrow$ Backbone encoder $\rightarrow$ MTL head variant $\rightarrow$ Evaluation metrics

Dataset	Head variant	Head detail	Training method
GLUE (Frozen BERT backbone)	Classical MTL head	1 linear layer per task	Task-sampled MTL (with capped batches and LR scheduler) Classification: BCEWithLogitsLoss , CrossEntropyLoss , Regression: MSELoss
	HQNN (4 or 10 qubits)	VQC ( Phukan et al., 2024 ) followed by 1 linear layer per task
	QMTL (10 qubits)	QMTL head ( $S_{1\to 8}=1$ & $S_{9}=2$ )
CheXpert (DenseNet121 backbone)	Classical MTL head	1 linear layer per task	Parallel tasks MTL Masked loss for missing labels; Class-weighted focal loss (Appendix Eq. 24 ) 3-class train, binary evaluations
	HQNN (4 or 10 qubits)	VQC ( Phukan et al., 2024 ) followed by 1 linear layer per task
	QMTL (10 qubits)	QMTL head ( $S_{t}=2$ for all tasks)

Table 1: Summary of model variants, backbone configuration, and training procedures used across datasets. Detailed hyperparameters are provided in Appendix 12 .

Figure 4: Total trainable parameters in task-specific heads across datasets. QMTL can achieve more than $12\times$ reduction compared to classical and 4-5 $\times$ compared to HQNN (when scaled to equivalent qubit count)

Panel of Figure 5 — Figure 5: Multi-task performance on the GLUE benchmark across four MTL head variants

Figure 6: Multi-task performance on the CheXpert dataset across four MTL head variants

Figure 7: Multi-task performance on the Extended MUStARD dataset across four MTL head variants

Figure 8: Effect of increasing parameter cost on model performance. The blue linegraph represents the trend observed when varying the encoding layer depth $L\in\{2,3,4\}$ , while keeping the task-specific subcircuit depth $L_{h}=1$ . The orange linegraph shows the trend when we vary the task-specific subcircuit depth $L_{h}\in\{1,2,3\}$ and keep the encoding layer depth $L=3$ . A moderately deep encoding subcircuit coupled with shallow task-specific subcircuits provides the best performance, highlighting the best balance between expressivity of the shared quantum representation and parameter efficiency.

Figure 9: Effect of entanglement in the shared encoder on QMTL performance across CheXpert tasks. These results suggest that entanglement in the shared encoder can improve the multi-task performance of QMTL.

Figure 10: Multi-task performance of QMTL on the CheXpert dataset under increasing depolarizing noise levels in AerSimulator . Accuracy (top) and F1-score (bottom) are reported across CheXpert tasks using identical trained weights.

Figure 11: Multi-task performance of QMTL on IBM Quantum devices ( ibm_fez , ibm_boston ) compared to noise-free statevector simulation ( default.qubit ). Accuracy (top) and F1-score (bottom) are reported across the CheXpert tasks using the same trained weights. ibm_boston performs closer to the ideal simulation than ibm_fez

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Dataset	Modality	# tasks	Task Type	# samples	Labeling scheme
GLUE Benchmark	Text (NLP)	9	Binary, Multiclass, Regression	$\leq 300k$ per task	Exactly 1-labeled task per sample
CheXpert	Chest X-ray (image)	5	Binary	$20$ k total	$\geq 1$ labeled task per sample
Extended MUStARD	Multimodal (audio, text, visual)	5	Binary, Multiclass	$690$ total	Fully labeled

Appendix

Table 2: Summary of datasets considered in this paper for comparing our proposed QMTL architecture against baselines.

Dataset	Task	Metrics
CheXpert	Atelectasis †	Acc, P, R, F1
	Cardiomegaly †	Acc, P, R, F1
	Consolidation †	Acc, P, R, F1
	Edema †	Acc, P, R, F1
	Pleural Effusion †	Acc, P, R, F1
GLUE	COLA †	Matthews_corr, Acc

Appendix

Table 3: Summary of datasets, tasks, and evaluation metrics used across experiments. Symbols denote task types:

\dagger

= Binary classification,

\ddagger

= 3-class classification,

\clubsuit

= 9-class classification,

\triangle

= Regression. Abbreviations: Acc = Accuracy, P = Precision, R = Recall, F1 = F1-score, Matthews_corr = Matthews Correlation, Spearman = Spearman correlation, Pearson = Pearson correlation. For GLUE tasks, the primary metric is listed first.

Explore similar work

Federating Quantum and Classical Computing: A Privacy-Preserving Hybrid Approach
Sep 18, 2026Carlos Cano, Daniel M. Jimenez-Gutierrez, Diego Sal +4Quantum Machine Learning Hybrid Quantum-Classical ML
Hybrid Quantum Temporal Convolutional Networks
Feb 27, 2026Junghoon Justin Park, Maria Pak, Sebin Lee +4Quantum Machine Learning Hybrid Quantum-Classical ML
Seoul National University Seoul, Korea · Wells Fargo New York, USA · Brookhaven National Laboratory New York, USA
Parameter-Efficient Quantum NLP for Paraphrase Detection: Performance, Robustness, and Entanglement
Sep 13, 2026Farha Nausheen, Khandakar Ahmed, Farina RiazQuantum Machine Learning Hybrid Quantum-Classical ML
ISILC, Victoria University, Melbourne, VIC, Australia · CSIRO, Australian International Institute of Higher Education, Sydney, NSW, Australia

Sep 18, 2026J/K move · Enter open · S save

Federating Quantum and Classical Computing: A Privacy-Preserving Hybrid Approach

Carlos Cano, Daniel M. Jimenez-Gutierrez, Diego Sal, Georgios Kellaris+3

Quantum Machine Learning Hybrid Quantum-Classical ML Federated Learning

Open paper AskPDF arXiv

Quantum machine learning (QML) is increasingly recognized as one of the most promising near-term applications of quantum computing, viewed as a next-frontier candidate beyond purely classical approaches. Hybrid quantum-classical models operationalize this potential by embedding a parameterized quantum circuit within a model where all other components remain classical-a design already applied to chemistry simulation, financial modeling, and image classification. However, their deployment in privacy-sensitive, multi-party settings is constrained by the need to avoid centralizing raw data and by the requirement that modern quantum circuits remain parameter-efficient to stay trainable at scale. In this paper, we address these constraints by evaluating federated learning (FL) as a means of combining a hybrid quantum-classical active party with a classical passive party, using Sherpa.ai's Blind Vertical FL (SBVFL) protocol to avoid centralizing raw data, while drastically reducing communication. We construct the split multiplicative periodic parity (SMPP) benchmark, following common QML design practice. On this task, our simulations show that SBVFL raises accuracy from 0.7227 to 0.8757 compared to local training, closely approaching non-private centralized accuracy, and that the hybrid quantum-classical model achieves this with substantially fewer trainable parameters than the classical neural networks and random forest alternatives. These results show that FL enables high-performing, privacy-preserving quantum-classical collaboration without centralizing raw data.

Abstract

Explore similar work

Federating Quantum and Classical Computing: A Privacy-Preserving Hybrid Approach

Hybrid Quantum Temporal Convolutional Networks

Parameter-Efficient Quantum NLP for Paraphrase Detection: Performance, Robustness, and Entanglement