标题： AdaBridge：用于边缘系统中高效多任务DNN协同进化的动态数据和计算重用 显示英文标题

标题： AdaBridge: Dynamic Data and Computation Reuse for Efficient Multi-task DNN Co-evolution in Edge Systems

摘要： 在移动设备上运行多任务DNN是各种应用（如自动驾驶和移动自然语言处理）的新兴趋势。 移动DNN通常被压缩以适应有限的资源，因此由于数据漂移而遭受准确性与泛化能力的下降。 DNN进化，例如持续学习和领域自适应，在克服这些问题方面已被证明是有效的，主要用于单任务DNN，而多任务DNN进化仍然是一个重要的开放挑战。 为了填补这一空白，我们提出了AdaBridge，它利用多任务DNN中的计算冗余作为动态数据和计算重用的独特机会，从而在边缘系统中异步多任务共同进化中提高训练效率和资源效率。 实验评估表明，AdaBridge在个体进化基线上实现了11%的平均准确率提升。 显示英文摘要

摘要： Running multi-task DNNs on mobiles is an emerging trend for various applications like autonomous driving and mobile NLP. Mobile DNNs are often compressed to fit the limited resources and thus suffer from degraded accuracy and generalizability due to data drift. DNN evolution, e.g., continuous learning and domain adaptation, has been demonstrated effective in overcoming these issues, mostly for single-task DNN, leaving multi-task DNN evolution an important yet open challenge. To fill up this gap, we propose AdaBridge, which exploits computational redundancies in multi-task DNNs as a unique opportunity for dynamic data and computation reuse, thereby improving training efficacy and resource efficiency among asynchronous multi-task co-evolution in edge systems. Experimental evaluation shows that AdaBridge achieves 11% average accuracy gain upon individual evolution baselines.