SC22 Proceedings

The International Conference for High Performance Computing, Networking, Storage, and Analysis

Research Posters Archive

CLIP-ACQUA: CLIP Autoencoder-Based Classic-Quantum Latent Space Reduction


Authors: Pablo Rivas (Baylor University) and Liang Zhao (St Ambrose University)

Abstract: Applications of quantum machine learning algorithms are currently still being studied. Recent work suggests that classical gradient descent techniques can effectively train variational quantum circuits. We propose to train quantum variational circuits to find smaller text and image embeddings that preserve contrastive-learning distances based on CLIP large embeddings. This is a critical task since fine-tuning CLIP to produce low-dimensional embeddings is prohibitively expensive. We introduce CLIP-ACQUA, a model trained in a self-supervised configuration from CLIP embeddings to reduce the latent space. We use CLIP-ACQUA on a sizeable unlabelled corpus of text and images to demonstrate its effectiveness. Our experiments show that we can obtain smaller latent spaces that preserve the original embedding distances inferred during contrastive learning. Furthermore, using our model requires no fine-tuning of CLIP, preserving its original robustness and structure. The data used as a demonstration aids in modeling consumer-to-consumer online marketplaces to detect illicit activities.

Best Poster Finalist (BP): no

Poster: PDF
Poster summary: PDF


Back to Poster Archive Listing