Binarized Knowledge Graph Embeddings
Binarized Knowledge Graph Embeddings
复制标题
DOI：
10.1007/978-3-030-15712-8_12
复制
发表时间：
2019-02
期刊：
影响因子：
--
通讯作者：
Koki Kishimoto;K. Hayashi;Genki Akai;M. Shimbo;Kazunori Komatani
中科院分区：
文献类型：
--
作者：
Koki Kishimoto;K. Hayashi;Genki Akai;M. Shimbo;Kazunori Komatani
张量因子分解已经成为知识图完成（KGC）的一种越来越流行的方法，KGC是自动预测知识图中缺失事实的任务。然而，即使使用像CANDECOMP/PARAFAC（CP）张量分解这样的简单模型，现有知识图上的KGC在资源有限的环境中也是不切实际的，因为需要大量的内存来存储表示为32位或64位浮点数的参数。随着现有知识图谱的规模不断扩大，这一限制预计将变得更加严格。为了减少内存需求，我们提出了一种方法，通过引入一个量化函数的优化问题的CP张量分解的参数进行二值化。该方法在训练后将浮点值参数替换为二进制参数，从而在运行时大大减小了模型大小。我们研究了几个KGC基准数据集的张量分解模型的质量和大小之间的权衡。在我们的实验中，所提出的方法成功地将模型大小减少了一个数量级以上，同时保持了任务性能。此外，可以利用逐位操作开发快速分数计算技术。
Tensor factorization has become an increasingly popular approach to knowledge graph completion (KGC), which is the task of automatically predicting missing facts in a knowledge graph. However, even with a simple model like CANDECOMP/PARAFAC (CP) tensor decomposition, KGC on existing knowledge graphs is impractical in resource-limited environments, as a large amount of memory is required to store parameters represented as 32-bit or 64-bit floating point numbers. This limitation is expected to become more stringent as existing knowledge graphs, which are already huge, keep steadily growing in scale. To reduce the memory requirement, we present a method for binarizing the parameters of the CP tensor decomposition by introducing a quantization function to the optimization problem. This method replaces floating point–valued parameters with binary ones after training, which drastically reduces the model size at run time. We investigate the trade-off between the quality and size of tensor factorization models for several KGC benchmark datasets. In our experiments, the proposed method successfully reduced the model size by more than an order of magnitude while maintaining the task performance. Moreover, a fast score computation technique can be developed with bitwise operations.