A CONCEPTUAL FRAMEWORK FOR ROBUST FEW-SHOT LEARNING: INTEGRATING UNBALANCED OPTIMAL TRANSPORT AND SELF-SUPERVISED TRANSFORMER REPRESENTATIONS

Authors

• Hayati Abd Rahman, Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA (UiTM), Shah Alam, MalaysiaFollow
• Pang Yun, Guilin University of Electronic Technology, Beihai, Guangxi, ChinaFollow

Abstract

Few-shot learning (FSL) aims to enable deep models to generalise from extremely limited labelled data, yet unstable metric matching, distribution imbalances, and weak structural representations in low-data regimes often constrain its performance. This paper proposes a conceptual framework that unifies metric-based similarity learning, Unbalanced Optimal Transport (UOT) via Unbalanced Sinkhorn Distance (USD), and self-supervised Transformer representations to conceptually address the theoretical and structural limitations of existing FSL approaches. The framework theoretically unifies distribution-aware USD matching, SSL-enhanced ViT/Swin feature representations, and metric-based inference within a coherent pipeline. This work aims to provide a theoretical foundation and research roadmap for future empirical studies on robust few-shot learning under realistic, distributionally complex conditions.

Digital Object Identifier (DOI)

10.24191/mjoc.vo11i1.9616

Publication Date

4-1-2026

Volume

11

Issue

1

Recommended Citation

Abd Rahman, Hayati and Yun, Pang (2026) "A CONCEPTUAL FRAMEWORK FOR ROBUST FEW-SHOT LEARNING: INTEGRATING UNBALANCED OPTIMAL TRANSPORT AND SELF-SUPERVISED TRANSFORMER REPRESENTATIONS," Malaysian Journal of Computing (MJoC): Vol. 11: Iss. 1, Article 4.

Available at: https://mjoc.researchcommons.org/journal/vol11/iss1/4