paper-with-me

Papers

Quantum-inspired Embeddings Projection and Similarity Metrics for Representation Learning

2025-01-08 · Ivan Kankeu, Stefan Gerd Fritsch, Gunnar Schönhoff, Elie Mounzer, Paul Lukowicz, Maximilian Kiefer-Emmanouilidis

Over the last decade, representation learning, which embeds complex information extracted from large amounts of data into dense vector spaces, has emerged as a key technique in machine learning. Among other applications, it has been a key building block for large language models and advanced computer vision systems based on contrastive learning. A core component of representation learning systems is the projection head, which maps the original embeddings into different, often compressed spaces, while preserving the similarity relationship between vectors. In this paper, we propose a quantum-inspired projection head that includes a corresponding quantum-inspired similarity metric. Specifically, we map classical embeddings onto quantum states in Hilbert space and introduce a quantum circuit-based projection head to reduce embedding dimensionality. To evaluate the effectiveness of this approach, we extended the BERT language model by integrating our projection head for embedding compression. We compared the performance of embeddings, which were compressed using our quantum-inspired projection head, with those compressed using a classical projection head on information retrieval tasks using the TREC 2019 and TREC 2020 Deep Learning benchmarks. The results demonstrate that our quantum-inspired method achieves competitive performance relative to the classical method while utilizing 32 times fewer parameters. Furthermore, when trained from scratch, it notably excels, particularly on smaller datasets. This work not only highlights the effectiveness of the quantum-inspired approach but also emphasizes the utility of efficient, ad hoc low-entanglement circuit simulations within neural networks as a powerful quantum-inspired technique.

📄 PDF Abstract BibTeX arXiv:2501.04591

Code (1)

ivpb/qiepsm 공식 구현 pytorch

Tasks

Contrastive LearningInformation RetrievalRepresentation Learning

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

Reverse Map Projections as Equivariant Quantum Embeddings

2024-07-29 · Max Arnott, Dimitri Papaioannou, Kieran McDowall, Phalgun Lolur 외

We introduce the novel class $(E_\alpha)_{\alpha \in [-\infty,1)}$ of reverse map projection embeddings, each one defining a unique new method of encoding classical data into quantum states. Inspired by well-known map pr…

Quantum Machine Learning

On the Representational Limits of Quantum-Inspired 1024-D Document Embeddings: An Experimental Evaluation Framework

2026-04-10 · Dario Maio arxiv

Text embeddings are central to modern information retrieval and Retrieval-Augmented Generation (RAG). While dense models derived from Large Language Models (LLMs) dominate current practice, recent work has explored quant…

Information Retrieval

Learning Complex Word Embeddings in Classical and Quantum Spaces

2024-12-18 · Carys Harvey, Stephen Clark, Douglas Brown, Konstantinos Meichanetzidis

We present a variety of methods for training complex-valued word embeddings, based on the classical Skip-gram model, with a straightforward adaptation simply replacing the real-valued vectors with arbitrary vectors of co…

C++ codeWord Embeddings

SMILES-Inspired Transfer Learning for Quantum Operators in Generative Quantum Eigensolver

2025-09-24 · Zhi Yin, Xiaoran Li, Shengyu Zhang, Xin Li 외 arxiv

Given the inherent limitations of traditional Variational Quantum Eigensolver(VQE) algorithms, the integration of deep generative models into hybrid quantum-classical frameworks, specifically the Generative Quantum Eigen…

Transfer Learning

How Embeddings Shape Graph Neural Networks: Classical vs Quantum-Oriented Node Representations

2026-04-16 · Nouhaila Innan, Antonello Rosato, Alberto Marchisio, Muhammad Shafique arxiv

Node embeddings act as the information interface for graph neural networks, yet their empirical impact is often reported under mismatched backbones, splits, and training budgets. This paper provides a controlled benchmar…

Graph ClassificationGraph Learning