Continual Multimodal Knowledge Graph Construction
This addresses a key limitation for applications requiring dynamic knowledge graphs from multimedia data, though it appears incremental as it builds on continual learning and multimodal methods.
The paper tackles the problem of catastrophic forgetting in Multimodal Knowledge Graph Construction (MKGC) when dealing with continuously emerging entities and relations, introducing the MSPT framework that outperforms existing methods by balancing knowledge retention and new data integration.
Current Multimodal Knowledge Graph Construction (MKGC) models struggle with the real-world dynamism of continuously emerging entities and relations, often succumbing to catastrophic forgetting-loss of previously acquired knowledge. This study introduces benchmarks aimed at fostering the development of the continual MKGC domain. We further introduce MSPT framework, designed to surmount the shortcomings of existing MKGC approaches during multimedia data processing. MSPT harmonizes the retention of learned knowledge (stability) and the integration of new data (plasticity), outperforming current continual learning and multimodal methods. Our results confirm MSPT's superior performance in evolving knowledge environments, showcasing its capacity to navigate balance between stability and plasticity.