HYPER^2：用于超关系链接预测的双曲Poincare嵌入
HYPER^2: Hyperbolic Poincare Embedding for Hyper-Relational Link Prediction
摘要：
链接预测，解决了与缺失的事实，完成KG的问题，已被广泛研究。然而，对无处不在的超关系型幼儿园的了解较少。大多数现有的超关系KG嵌入模型仍然将n元事实撕裂成更小的元组，忽略了一些n元事实的不可分解性。而其他框架只对某些arity事实起作用，或者忽略了primary triple的重要性。在本文中，我们表示一个n元事实作为一个整体，同时保持了n元事实的完整性和维护的重要作用，主要三元组。此外，我们还将双曲Poincaré嵌入从二元数据推广到了任意元数据，这是一个尚未被研究过的问题。为了解决弱表达性和高复杂性的问题，我们提出了HYPER^2，它通过切空间上的信息聚合来捕获三元组内外实体之间的交互。大量的实验表明，HYPER^2实现了优于其翻译和深度类似物的性能，在相对较少的维度下将SOTA提高了34.5%。此外，我们还研究了文字的副作用，并从理论和实验上比较了HYPER^2的计算复杂性与几个性能最好的基线，HYPER^2是49-61倍快于它的同行。
英文摘要：
Link Prediction, addressing the issue of completing KGs with missing facts, has been broadly studied. However, less light is shed on the ubiquitous hyper-relational KGs. Most existing hyper-relational KG embedding models still tear an n-ary fact into smaller tuples, neglecting the indecomposability of some n-ary facts. While other frameworks work for certain arity facts only or ignore the significance of primary triple. In this paper, we represent an n-ary fact as a whole, simultaneously keeping the integrity of n-ary fact and maintaining the vital role that the primary triple plays. In addition, we generalize hyperbolic Poincaré embedding from binary to arbitrary arity data, which has not been studied yet. To tackle the weak expressiveness and high complexity issue, we propose HYPER^2 which is qualified for capturing the interaction between entities within and beyond triple through information aggregation on the tangent space. Extensive experiments demonstrate HYPER^2 achieves superior performance to its translational and deep analogues, improving SOTA by up to 34.5\% with relatively few dimensions. Moreover, we study the side effect of literals and we theoretically and experimentally compare the computational complexity of HYPER^2 against several best performing baselines, HYPER^2 is 49-61 times quicker than its counterparts.
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。
