动态稀疏训练中，通过拓扑感知恢复提升静态稀疏模型性能。
Topology-Aware Revival for Efficient Sparse Training
- 基于拓扑需求分配少量复活预算，单次激活被剪枝连接。
- 在SAC和TD3算法上，最高提升37.9%最终回报。
- 无需动态重连，适合深度强化学习场景使用。
静态稀疏训练通过固定掩码模式实现高效学习，但受限结构降低了鲁棒性。早期剪枝决策会使网络陷入脆弱结构，难以摆脱，尤其在深度强化学习中，演化策略持续改变训练分布。我们提出拓扑感知恢复（TAR），一种轻量级一次性后剪枝方法，在不依赖动态重连的情况下提升静态稀疏性。剪枝后，TAR根据各层拓扑需求分配少量复活预算，随机均匀地在每层重新激活少数被剪枝连接，随后固定该连接结构直至训练结束。在多个连续控制任务中，使用SAC和TD3算法，TAR相较静态稀疏基线最高提升37.9%的最终回报，并在中位数上超越动态稀疏训练基线13.5%。
原文摘要 · Abstract (English)
Static sparse training is a promising route to efficient learning by committing to a fixed mask pattern, yet the constrained structure reduces robustness. Early pruning decisions can lock the network into a brittle structure that is difficult to escape, especially in deep reinforcement learning (RL) where the evolving policy continually shifts the training distribution. We propose Topology-Aware Revival (TAR), a lightweight one-shot post-pruning procedure that improves static sparsity without dynamic rewiring. After static pruning, TAR performs a single revival step by allocating a small reserve budget across layers according to topology needs, randomly uniformly reactivating a few previously pruned connections within each layer, and then keeping the resulting connectivity fixed for the remainder of training. Across multiple continuous-control tasks with SAC and TD3, TAR improves final return over static sparse baselines by up to +37.9% and also outperforms dynamic sparse training baselines with a median gain of +13.5%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。