IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911856904372224 |
|---|---|
| author | Bhat, Prashant Renjith, Bharath Arani, Elahe Zonooz, Bahram |
| author_facet | Bhat, Prashant Renjith, Bharath Arani, Elahe Zonooz, Bahram |
| contents | Continual learning (CL) remains one of the long-standing challenges for deep neural networks due to catastrophic forgetting of previously acquired knowledge. Although rehearsal-based approaches have been fairly successful in mitigating catastrophic forgetting, they suffer from overfitting on buffered samples and prior information loss, hindering generalization under low-buffer regimes. Inspired by how humans learn using strong inductive biases, we propose IMEX-Reg to improve the generalization performance of experience rehearsal in CL under low buffer regimes. Specifically, we employ a two-pronged implicit-explicit regularization approach using contrastive representation learning (CRL) and consistency regularization. To further leverage the global relationship between representations learned using CRL, we propose a regularization strategy to guide the classifier toward the activation correlations in the unit hypersphere of the CRL. Our results show that IMEX-Reg significantly improves generalization performance and outperforms rehearsal-based approaches in several CL scenarios. It is also robust to natural and adversarial corruptions with less task-recency bias. Additionally, we provide theoretical insights to support our design decisions further. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18161 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learning Bhat, Prashant Renjith, Bharath Arani, Elahe Zonooz, Bahram Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Continual learning (CL) remains one of the long-standing challenges for deep neural networks due to catastrophic forgetting of previously acquired knowledge. Although rehearsal-based approaches have been fairly successful in mitigating catastrophic forgetting, they suffer from overfitting on buffered samples and prior information loss, hindering generalization under low-buffer regimes. Inspired by how humans learn using strong inductive biases, we propose IMEX-Reg to improve the generalization performance of experience rehearsal in CL under low buffer regimes. Specifically, we employ a two-pronged implicit-explicit regularization approach using contrastive representation learning (CRL) and consistency regularization. To further leverage the global relationship between representations learned using CRL, we propose a regularization strategy to guide the classifier toward the activation correlations in the unit hypersphere of the CRL. Our results show that IMEX-Reg significantly improves generalization performance and outperforms rehearsal-based approaches in several CL scenarios. It is also robust to natural and adversarial corruptions with less task-recency bias. Additionally, we provide theoretical insights to support our design decisions further. |
| title | IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learning |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.18161 |