packnet

**PackNet** is **a pruning-based continual-learning method that allocates disjoint parameter subsets to sequential tasks** - After training a task, important weights are fixed and remaining free weights are reused for later tasks. **What Is PackNet?** - **Definition**: A pruning-based continual-learning method that allocates disjoint parameter subsets to sequential tasks. - **Core Mechanism**: After training a task, important weights are fixed and remaining free weights are reused for later tasks. - **Operational Scope**: It is applied during data scheduling, parameter updates, or architecture design to preserve capability stability across many objectives. - **Failure Modes**: Aggressive pruning can reduce headroom for future tasks and harm final adaptability. **Why PackNet Matters** - **Retention and Stability**: It helps maintain previously learned behavior while new tasks are introduced. - **Transfer Efficiency**: Strong design can amplify positive transfer and reduce duplicate learning across tasks. - **Compute Use**: Better task orchestration improves return from fixed training budgets. - **Risk Control**: Explicit monitoring reduces silent regressions in legacy capabilities. - **Program Governance**: Structured methods provide auditable rules for updates and rollout decisions. **How It Is Used in Practice** - **Design Choice**: Select the method based on task relatedness, retention requirements, and latency constraints. - **Calibration**: Tune pruning ratios per task stage and validate both retained-task accuracy and future-task capacity. - **Validation**: Track per-task gains, retention deltas, and interference metrics at every major checkpoint. PackNet is **a core method in continual and multi-task model optimization** - It enables sequential task learning with explicit parameter ownership boundaries.