Learning Shared Representations From Unpaired Data

Abstract

Learning shared representations is a primary area of multimodal representation learning. The current approaches to achieve a shared embedding space rely heavily on paired samples from each modality, which are significantly harder to obtain than unpaired ones. In this work, we demonstrate that shared representations can be learned almost exclusively from unpaired data. Our arguments are grounded in the spectral embeddings of the random walk matrices constructed independently from each unimodal representation. Empirical results in computer vision and natural language processing domains support its potential, revealing the effectiveness of unpaired data in capturing meaningful cross-modal relations, demonstrating high capabilities in retrieval tasks, generation, arithmetics, zero-shot, and cross-domain classification. This work, to the best of our knowledge, is the first to demonstrate these capabilities almost exclusively from unpaired samples, giving rise to a cross-modal embedding that

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyacobi2025learning

Related papers

• Cross-modal Discrete Representation Learning (2021)10.61
• Joint Representation Learning And Novel Category Discovery On Single- And Multi-modal Data (2021)13.11
• Learning Unseen Modality Interaction (2023)0.00
• Multimodal Representation Learning Conditioned On Semantic Relations (2025)0.00
• Multimodal Representation Alignment For Cross-modal Information Retrieval (2025)0.00
• Adversarial Cross-modal Retrieval Via Learning And Transferring Single-modal Similarities (2019)8.60
• Using Multiple Instance Learning To Build Multimodal Representations (2022)4.52
• ASIF: Coupled Data Turns Unimodal Models To Multimodal Without Training (2022)0.00