论文标题
神经群体测试以加速深度学习
Neural Group Testing to Accelerate Deep Learning
论文作者
论文摘要
深度学习的最新进展使使用了数以百万个参数的大型深层神经网络。这些网络的巨大规模在推断过程中施加了挑战性的计算负担。现有的工作主要侧重于加速神经网络的每个前进通行证。受到有效疾病测试的小组测试策略的启发，我们提出了神经群体测试，该测试通过在一次前传中测试一组样品来加速。排除了测试阴性样本的组。如果组测试呈阳性，则该组中的样本会自适应地重新测试。神经群体测试的一个主要挑战是修改深神网络，以便它可以在一个正向传球中测试多个样本。我们提出了三种设计来实现此目标的设计，而无需引入任何新参数并评估其性能。我们在图像中的任务中应用神经群测试来检测罕见但不适当的图像。我们发现，神经群测试可以在一次前传中分组多达16张图像，并在提高检测性能的同时将整体计算成本降低超过73％。
Recent advances in deep learning have made the use of large, deep neural networks with tens of millions of parameters. The sheer size of these networks imposes a challenging computational burden during inference. Existing work focuses primarily on accelerating each forward pass of a neural network. Inspired by the group testing strategy for efficient disease testing, we propose neural group testing, which accelerates by testing a group of samples in one forward pass. Groups of samples that test negative are ruled out. If a group tests positive, samples in that group are then retested adaptively. A key challenge of neural group testing is to modify a deep neural network so that it could test multiple samples in one forward pass. We propose three designs to achieve this without introducing any new parameters and evaluate their performances. We applied neural group testing in an image moderation task to detect rare but inappropriate images. We found that neural group testing can group up to 16 images in one forward pass and reduce the overall computation cost by over 73% while improving detection performance.
