Different patterns of environmental change (space vs time) require different LLM update behaviors; no single family of methods—prompts, distillation, RL, or compression—handles all regimes.
Continual Learning via Neural Pruning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification. In this method, subsequent tasks are trained using the inactive neurons and filters of the sparsified network and cause zero deterioration to the performance of previous tasks. In order to deal with the possible compromise between model sparsity and performance, we formalize and incorporate the concept of graceful forgetting: the idea that it is preferable to suffer a small amount of forgetting in a controlled manner if it helps regain network capacity and prevents uncontrolled loss of performance during the training of future tasks. CLNP also provides simple continual learning diagnostic tools in terms of the number of free neurons left for the training of future tasks as well as the number of neurons that are being reused. In particular, we see in experiments that CLNP verifies and automatically takes advantage of the fact that the features of earlier layers are more transferable. We show empirically that CLNP leads to significantly improved results over current weight elasticity based methods.
representative citing papers
Integrates SAM-Audio dense representations with guided attention and dual distillation for audio-visual class-incremental learning, reporting consistent outperformance on benchmarks.
SOR-SNN employs Self-Organizing Regulation networks to reorganize a single SNN into sparse pathways, achieving better performance, energy efficiency, memory use, backward transfer, and self-repair on continual learning tasks including CIFAR100 and ImageNet.
citing papers explorer
-
When Does Continual Learning Require Learning
Different patterns of environmental change (space vs time) require different LLM update behaviors; no single family of methods—prompts, distillation, RL, or compression—handles all regimes.
-
Listen, Look, and Learn: Learning Without Forgetting through SAM-Audio
Integrates SAM-Audio dense representations with guided attention and dual distillation for audio-visual class-incremental learning, reporting consistent outperformance on benchmarks.
-
Adaptive Reorganization of Neural Pathways for Continual Learning with Spiking Neural Networks
SOR-SNN employs Self-Organizing Regulation networks to reorganize a single SNN into sparse pathways, achieving better performance, energy efficiency, memory use, backward transfer, and self-repair on continual learning tasks including CIFAR100 and ImageNet.