获得深度匹配：稀疏二进制input/output网络的Bloom嵌入
Getting deep recommenders fit: Bloom embeddings for sparse binary input/output networks
摘要：
结合了深度学习技术的推荐算法正变得越来越流行。由于来自推荐域的数据的结构（即，项目偏好的独热编码向量），这些算法倾向于具有支配其总体大小的大输入和输出维度。由于图形处理单元的存储器有限，这使得它们难以训练，并且难以在具有有限硬件的移动设备上部署。为了解决这些困难，我们提出了布卢姆嵌入，压缩技术，可应用于神经网络模型的输入和输出处理稀疏高维二进制编码的实例。Bloom嵌入在计算上是高效的，并且在高达1/5的压缩比下不会严重损害模型的准确性。在某些情况下，它们甚至比原来的精度有所提高，相对提高高达12%。我们在7个数据集上评估了Bloom嵌入，并将其与4种替代方法进行了比较，获得了良好的结果。我们还讨论了一些进一步的优势，布鲁姆嵌入，如“在飞行”的恒定时间操作，零或边际空间要求，训练时间加速，或事实上，他们不需要任何改变的核心模型架构或训练配置。
英文摘要：
Recommendation algorithms that incorporate techniques from deep learning are becoming increasingly popular. Due to the structure of the data coming from recommendation domains (i.e., one-hot-encoded vectors of item preferences), these algorithms tend to have large input and output dimensionalities that dominate their overall size. This makes them difficult to train, due to the limited memory of graphical processing units, and difficult to deploy on mobile devices with limited hardware. To address these difficulties, we propose Bloom embeddings, a compression technique that can be applied to the input and output of neural network models dealing with sparse high-dimensional binary-coded instances. Bloom embeddings are computationally efficient, and do not seriously compromise the accuracy of the model up to 1/5 compression ratios. In some cases, they even improve over the original accuracy, with relative increases up to 12%. We evaluate Bloom embeddings on 7 data sets and compare it against 4 alternative methods, obtaining favorable results. We also discuss a number of further advantages of Bloom embeddings, such as 'on-the-fly' constant-time operation, zero or marginal space requirements, training time speedups, or the fact that they do not require any change to the core model architecture or training configuration.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
