MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914027166236672 |
|---|---|
| author | You, Haochen Liu, Baojing |
| author_facet | You, Haochen Liu, Baojing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06219 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learning You, Haochen Liu, Baojing Machine Learning Multimedia 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. |
| title | MCIGLE: Multimodal Exemplar-Free Class-Incremental Graph Learning |
| topic | Machine Learning Multimedia |
| url | https://arxiv.org/abs/2509.06219 |