arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.04723cs.LGcs.AI
收藏

关系数据的神经网络

Neural Networks for Relational Data

The University of Texas at Dallas(德克萨斯大学达拉斯分校);Amazon Inc.(亚马逊公司);TU Darmstadt(达姆施塔特工业大学)

Navdeep Kaur, Gautam Kunapuli, Saket Joshi, Kristian Kersting, Sriraam Natarajan

摘要:

虽然深度网络在过去十年中取得了巨大的成功,但它们依赖于平面特征向量表示,这使得它们不适用于结构丰富的领域,例如社会网络分析等应用中出现的领域。这些领域依赖于关系表示来捕获实体及其属性之间的复杂关系。因此,我们考虑学习神经网络的关系数据的问题。我们将自己与当前依赖于专家手工编码规则的方法区分开来,这些方法通过学习基于关系随机游走的特征来捕获局部结构相互作用和由此产生的网络架构。我们进一步利用所得到的关系神经网络的网络权重的参数绑定,其中相同类型的实例共享参数。我们在几个标准关系数据集上的实验结果证明了所提出的方法在多个神经网络基线以及最先进的统计关系模型上的有效性。

英文摘要:

While deep networks have been enormously successful over the last decade, they rely on flat-feature vector representations, which makes them unsuitable for richly structured domains such as those arising in applications like social network analysis. Such domains rely on relational representations to capture complex relationships between entities and their attributes. Thus, we consider the problem of learning neural networks for relational data. We distinguish ourselves from current approaches that rely on expert hand-coded rules by learning relational random-walk-based features to capture local structural interactions and the resulting network architecture. We further exploit parameter tying of the network weights of the resulting relational neural network, where instances of the same type share parameters. Our experimental results across several standard relational data sets demonstrate the effectiveness of the proposed approach over multiple neural net baselines as well as state-of-the-art statistical relational models.

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。

↑