MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learning
It addresses incremental learning for multimodal graphs, which is incremental as it builds on existing methods for a specific domain.
The paper tackles the problem of exemplar-free class-incremental learning for multimodal graph-structured data, addressing challenges like catastrophic forgetting and distribution bias, and reports that MCIGLE achieves validated effectiveness and generalizability on public datasets.
Exemplar-free class-incremental learning enables models to learn new classes over time without storing data from old ones. As multimodal graph-structured data becomes increasingly prevalent, existing methods struggle with challenges like catastrophic forgetting, distribution bias, memory limits, and weak generalization. We propose MCIGLE, a novel framework that addresses these issues by extracting and aligning multimodal graph features and applying Concatenated Recursive Least Squares for effective knowledge retention. Through multi-channel processing, MCIGLE balances accuracy and memory preservation. Experiments on public datasets validate its effectiveness and generalizability.