Triplet Loss Based Quantum Encoding for Class Separability

• URL: http://arxiv.org/abs/2509.15705v1
• Date: Fri, 19 Sep 2025 07:28:19 GMT
• Title: Triplet Loss Based Quantum Encoding for Class Separability
• Authors: Marco Mordacci, Mahul Pandey, Paolo Santini, Michele Amoretti,
• Abstract summary: The encoding circuit is trained using a triplet loss function inspired by classical facial recognition algorithms.<n> Benchmark tests performed on various binary classification tasks on MNIST and MedMNIST datasets demonstrate considerable improvement over amplitude encoding with the same VQC structure.
• Score: 2.7641963278515114
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: An efficient and data-driven encoding scheme is proposed to enhance the performance of variational quantum classifiers. This encoding is specially designed for complex datasets like images and seeks to help the classification task by producing input states that form well-separated clusters in the Hilbert space according to their classification labels. The encoding circuit is trained using a triplet loss function inspired by classical facial recognition algorithms, and class separability is measured via average trace distances between the encoded density matrices. Benchmark tests performed on various binary classification tasks on MNIST and MedMNIST datasets demonstrate considerable improvement over amplitude encoding with the same VQC structure while requiring a much lower circuit depth.

Related papers

• Unsupervised Deep Clustering of MNIST with Triplet-Enhanced Convolutional Autoencoders [0.0]
  This research implements an advanced unsupervised clustering system for MNIST handwritten digits.<n>A deep neural autoencoder requires a training process during phase one to develop minimal yet interpretive representations of images.
  arXiv  Detail & Related papers  (2025-06-11T18:26:13Z)
• An Efficient Quantum Classifier Based on Hamiltonian Representations [50.467930253994155]
  Quantum machine learning (QML) is a discipline that seeks to transfer the advantages of quantum computing to data-driven tasks.<n>We propose an efficient approach that circumvents the costs associated with data encoding by mapping inputs to a finite set of Pauli strings.<n>We evaluate our approach on text and image classification tasks, against well-established classical and quantum models.
  arXiv  Detail & Related papers  (2025-04-13T11:49:53Z)
• Data Encoding for VQC in Qiskit, A Comparison With Novel Hybrid Encoding [0.0]
  Amplitude encoding reduces the required qubits, Angle encoding makes state freedom better and is used for expressive encoding and Phase-based distinction.<n>This paper demonstrates that efficient qubit usage is ensured as Amplitude encoding reduces the required qubits, Angle encoding makes state freedom better and is used for expressive encoding and Phase-based distinction.
  arXiv  Detail & Related papers  (2025-03-18T09:36:09Z)
• Goal-Oriented Source Coding using LDPC Codes for Compressed-Domain Image Classification [3.2657732635702375]
  This paper investigates the use of low-density parity-check (LDPC) codes as an alternative entropy-coding approach.<n>It is hypothesized that the structured nature of LDPC codes can be leveraged more effectively by deep learning models for tasks like classification.<n>Experiments on datasets like MNIST, Fashion-MNIST, and CIFAR show that LDPC codes outperform Huffman and Arithmetic coding in classification tasks.
  arXiv  Detail & Related papers  (2025-03-15T01:52:09Z)
• Autoencoded UMAP-Enhanced Clustering for Unsupervised Learning [49.1574468325115]
  We propose a novel approach to unsupervised learning by constructing a non-linear embedding of the data into a low-dimensional space followed by any conventional clustering algorithm.<n>The embedding promotes clusterability of the data and is comprised of two mappings: the encoder of an autoencoder neural network and the output of UMAP algorithm.<n>When applied to MNIST data, AUEC significantly outperforms the state-of-the-art techniques in terms of clustering accuracy.
  arXiv  Detail & Related papers  (2025-01-13T22:30:38Z)
• Testing the Accuracy of Surface Code Decoders [55.616364225463066]
  Large-scale, fault-tolerant quantum computations will be enabled by quantum error-correcting codes (QECC) This work presents the first systematic technique to test the accuracy and effectiveness of different QECC decoding schemes.
  arXiv  Detail & Related papers  (2023-11-21T10:22:08Z)
• Encoding optimization for quantum machine learning demonstrated on a superconducting transmon qutrit [1.6460874590065597]
  Three-level quantum systems have the advantage of requiring fewer components than the typically used two-level qubits. This work investigates the potential of qutrit parametric circuits in machine learning classification applications.
  arXiv  Detail & Related papers  (2023-09-22T17:53:16Z)
• Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation [54.23510028456082]
  We propose a Triple-view Knowledge Distillation framework, termed TriKD, for semi-supervised semantic segmentation. The framework includes the triple-view encoder and the dual-frequency decoder.
  arXiv  Detail & Related papers  (2023-09-22T01:02:21Z)
• Deep Asymmetric Hashing with Dual Semantic Regression and Class Structure Quantization [9.539842235137376]
  We propose a dual semantic asymmetric hashing (DSAH) method, which generates discriminative hash codes under three-fold constrains. With these three main components, high-quality hash codes can be generated through network.
  arXiv  Detail & Related papers  (2021-10-24T16:14:36Z)
• EfficientFCN: Holistically-guided Decoding for Semantic Segmentation [49.27021844132522]
  State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN) We propose the EfficientFCN, whose backbone is a common ImageNet pre-trained network without any dilated convolution. Such a framework achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost.
  arXiv  Detail & Related papers  (2020-08-24T14:48:23Z)
• Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator [62.26981903551382]
  Variational auto-encoders (VAEs) with binary latent variables provide state-of-the-art performance in terms of precision for document retrieval. We propose a pairwise loss function with discrete latent VAE to reward within-class similarity and between-class dissimilarity for supervised hashing. This new semantic hashing framework achieves superior performance compared to the state-of-the-arts.
  arXiv  Detail & Related papers  (2020-05-21T06:11:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.