Model Releases
Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning
arXiv:2609.39839v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tunin
arXiv:2609.39839v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tuning with pre-trained models reduces parameter overhead but can suffer from cumulative interference and suboptimal alignment between inference samples and specialized modules. We propose Dynamic LoRA-Experts and Prototype-Ensemble Matching (DLEPEM), a two-stage rehearsal-free framework. DLEPEM allocates a task-specific LoRA-Expert for each incremental task to reduce cross-task interference, then combines frozen pre-trained-model prototypes with task-adaptive LoRA-Expert prototypes for reliable task-level discrimination. Experiments on standard CIL and Few-Shot CIL benchmarks demonstrate strong performance under the evaluated protocols.
Related
- Hyperbolic Prototype Routing for Rehearsal-Free Class-Incremental Learning
- Decoupled and Distilled: Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer for Few-Shot Class-Incremental Learning
- Uncertainty Is Not Enough: Value-of-Information Routing for Mixtures of LoRA Experts
- Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics
Source: arXiv cs.LG | 2026-10-01