ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation
ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation
复制标题
DOI：
10.1609/aaai.v33i01.3301265
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Jiankai Sun-;Bortik Bandyopadhyay;Armin Bashizade;Jiongqian Liang;P. Sadayappan;S. Parthasarathy
中科院分区：
文献类型：
--
作者：
Jiankai Sun-;Bortik Bandyopadhyay;Armin Bashizade;Jiongqian Liang;P. Sadayappan;S. Parthasarathy
有向图已广泛应用于社区问答服务（CQA）中，以对 CQA 图中不同类型节点（例如问题、答案、用户）之间的不对称关系进行建模。非对称传递性是有向图的一个基本属性，因为它可以在下游图推理和分析中发挥重要作用。问题难度和用户专业知识遵循不对称及物性的特征。保持这些属性，同时将图减少到较低维的向量嵌入空间，一直是最近研究的重点。在本文中，我们解决了具有不对称传递性保留的有向图嵌入的挑战，然后利用所提出的嵌入方法来解决 CQA 中的基本任务：如何将新发布的问题适当地路由和分配给具有适当专业知识和对 CQA 感兴趣的用户。该技术依赖于对此类图中的核心可达性和隐式层次结构进行操作的非线性变换，自然地结合了图层次结构和可达性信息。随后，该方法利用基于因式分解的方法为图中的每个节点生成两个嵌入向量，以捕获不对称传递性。大量实验表明，我们的框架在三个不同的现实世界任务上始终显着优于最先进的基线：链接预测、问题难度估计以及 Stack Exchange 等在线论坛中的专家查找。特别是，我们的框架可以支持新发布的问题（训练期间未见过的节点）的归纳嵌入学习，因此可以正确地将此类问题路由和分配给 CQA 中的专家。
Directed graphs have been widely used in Community Question Answering services (CQAs) to model asymmetric relationships among different types of nodes in CQA graphs, e.g., question, answer, user. Asymmetric transitivity is an essential property of directed graphs, since it can play an important role in downstream graph inference and analysis. Question difficulty and user expertise follow the characteristic of asymmetric transitivity. Maintaining such properties, while reducing the graph to a lower dimensional vector embedding space, has been the focus of much recent research. In this paper, we tackle the challenge of directed graph embedding with asymmetric transitivity preservation and then leverage the proposed embedding method to solve a fundamental task in CQAs: how to appropriately route and assign newly posted questions to users with the suitable expertise and interest in CQAs. The technique incorporates graph hierarchy and reachability information naturally by relying on a nonlinear transformation that operates on the core reachability and implicit hierarchy within such graphs. Subsequently, the methodology levers a factorization-based approach to generate two embedding vectors for each node within the graph, to capture the asymmetric transitivity. Extensive experiments show that our framework consistently and significantly outperforms the state-of-the-art baselines on three diverse realworld tasks: link prediction, and question difficulty estimation and expert finding in online forums like Stack Exchange. Particularly, our framework can support inductive embedding learning for newly posted questions (unseen nodes during training), and therefore can properly route and assign these kinds of questions to experts in CQAs.