N元关系知识库的广义张量分解
Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases
摘要：
随着知识库的迅速发展，链接预测任务，特别是在二元关系知识库（又称知识图谱）中，利用强有力的张量分解相关方法，完成含有缺失事实的知识库，得到了广泛的研究。然而，对于普遍存在的具有较高关联度的n元关联知识库，现有的基于翻译和神经网络的方法表达能力弱，建模复杂度高，而对这些知识库的研究较少。张量分解尚未被考虑用于n元关系知识库，而直接将二元关系知识库的张量分解相关方法扩展到n元情况并不产生令人满意的结果，这是由于指数模型的复杂性及其对二元关系的强假设。为了推广张量分解的n元关系知识库，在这项工作中，我们提出了GETD，基于Tucker分解和张量环分解的广义模型。现有的负采样技术也推广到n元的情况下GETD。此外，我们从理论上证明了GETD是完全表达，完全表示任何知识库。在两个具有代表性的n元关系KB数据集上的广泛评估表明，GETD的性能优越，显着提高了15%以上的最先进的方法。此外，GETD还在基准二元关系知识库数据集上获得了最新的结果。
英文摘要：
With the rapid development of knowledge bases (KBs), link prediction task, which completes KBs with missing facts, has been broadly studied in especially binary relational KBs (a.k.a knowledge graph) with powerful tensor decomposition related methods. However, the ubiquitous n-ary relational KBs with higher-arity relational facts are paid less attention, in which existing translation based and neural network based approaches have weak expressiveness and high complexity in modeling various relations. Tensor decomposition has not been considered for n-ary relational KBs, while directly extending tensor decomposition related methods of binary relational KBs to the n-ary case does not yield satisfactory results due to exponential model complexity and their strong assumptions on binary relations. To generalize tensor decomposition for n-ary relational KBs, in this work, we propose GETD, a generalized model based on Tucker decomposition and Tensor Ring decomposition. The existing negative sampling technique is also generalized to the n-ary case for GETD. In addition, we theoretically prove that GETD is fully expressive to completely represent any KBs. Extensive evaluations on two representative n-ary relational KB datasets demonstrate the superior performance of GETD, significantly improving the state-of-the-art methods by over 15\%. Moreover, GETD further obtains the state-of-the-art results on the benchmark binary relational KB datasets.
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。
