提出可定向增结构的网络，解决持续学习中的遗忘与统计冲突问题。
Directed Structural Adaptation to Overcome Statistical Conflicts and Enable Continual Learning
- 通过定向增结构突破数据统计冲突限制
- 网络性能高且规模远小于固定拓扑模型
- 无需任务标签即可检测并区分新旧任务
当前自适应网络依赖过参数化固定拓扑，难以克服数据中的统计冲突，且在持续学习中易发生灾难性遗忘。本文提出结构自适应方法DIRAD，可在需要时以定向方式复杂化网络，不受数据内统计冲突制约。进一步提出PREVAL框架，通过检测新数据并分配至适配模型，实现无任务标签的持续学习。实验表明，DIRAD可构建高性能网络，规模较固定拓扑小数个数量级；预研验证了PREVAL在不丢失旧知识前提下持续适应新任务的能力，具备识别已见任务的潜力。
原文摘要 · Abstract (English)
Adaptive networks today rely on overparameterized fixed topologies that cannot break through the statistical conflicts they encounter in the data they are exposed to, and are prone to "catastrophic forgetting" as the network attempts to reuse the existing structures to learn new task. We propose a structural adaptation method, DIRAD, that can complexify as needed and in a directed manner without being limited by statistical conflicts within a dataset. We then extend this method and present the PREVAL framework, designed to prevent "catastrophic forgetting" in continual learning by detection of new data and assigning encountered data to suitable models adapted to process them, without needing task labels anywhere in the workflow. We show the reliability of the DIRAD in growing a network with high performance and orders-of-magnitude simpler than fixed topology networks; and demonstrate the proof-of-concept operation of PREVAL, in which continual adaptation to new tasks is observed while being able to detect and discern previously-encountered tasks.
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。