Beyond the Ideal: Multimodal Learning with Imperfect Data Conditions

作者：Muhammad Irzam Liaqat · 发表于：Open MIND · 年份：2026 · DOI：10.13118/liaqat-muhammad-irzam_phd2026-05-14 · 研究领域：Computer science、Artificial intelligence、Machine learning

Multimodal learning combines heterogeneous data sources such as vision, audio, and text to improve perception and decision-making.Despite its empirical success, this thesis argues that multimodal learning is not inherently robust: most existing approaches assume the availability and reliability of all modalities, leading to significant performance degradation when modalities are missing or corrupted.Our work investigates how robustness in multimodal learning can be explicitly modeled and enforced under imperfect data conditions.It addresses three interconnected aspects: architectural design for modality integration, learning with missing modalities, and robustness to corrupted modalities.The contributions include unified taxonomies that reveal structural limitations of existing methods, a modality-agnostic learning framework that enables reliable inference under missing modalities, and principled benchmarks and models for evaluating and improving robustness under modality corruption.Overall, our work demonstrates that robustness in multimodal learning must be deliberately designed rather than assumed, and provides foundations for building reliable multimodal systems in real-world environments.