Recent years have seen rapid progress in network representation learning, which removes the need for burdensome feature engineering and facilitates downstream network-based tasks.

In reality, networks often exhibit heterogeneity, which means there may exist multiple types of nodes and interactions.

Heterogeneous networks raise new challenges to representation learning, as the awareness of node and edge types is required.

In this paper, we study a basic building block of general heterogeneous networks, the heterogeneous networks with two types of nodes. Many problems can be solved by decomposing general heterogeneous networks into multiple bipartite ones.

Recently, to overcome the demerits of non-metric measures used in the embedding space, metric learning-based approaches have been leveraged to tackle heterogeneous network representation learning.

These approaches first generate triplets of samples, in which an anchor node, a positive counterpart and a negative one co-exist, and then try to pull closer positive samples and push away negative ones.

However, when dealing with heterogeneous networks, even the simplest two-typed ones, triplets cannot simultaneously involve both positive and negative samples from different parts of networks.

To address this incompatibility of triplet-based metric learning, in this paper, we propose a novel quintuple-based method for learning node representations in bipartite heterogeneous networks.

Specifically, we generate quintuples that contain positive and negative samples from two different parts of networks. And we formulate two learning objectives that accommodate quintuple-based learning samples, a proximity-based loss that models the relations in quintuples by sigmoid probabilities, and an angular loss that more robustly maintains similarity structures.

In addition, we also parameterize feature learning by using one-dimensional convolution operators around nodes’ neighborhoods.

Compared with eight methods, extensive experiments on two downstream tasks manifest the effectiveness of our approach.

近年来，网络表示学习取得了快速进展，消除了繁琐的特征工程的需要，并促进了下游基于网络的任务。

实际上，网络经常表现出异构性，这意味着可能存在多种类型的节点和交互。

异构网络对表示学习提出了新的挑战，因为需要了解节点和边缘类型。

在本文中，我们研究了通用异构网络的基本构建块，即具有两种类型节点的异构网络。许多问题可以通过将一般异构网络分解为多个二分网络来解决。

最近，为了克服嵌入空间中使用的非度量测量的缺点，基于度量学习的方法已被用来解决异构网络表示学习。

这些方法首先生成样本三元组，其中锚节点、正对应项和负样本共存，然后尝试拉近正样本并推开负样本。

然而，在处理异构网络时，即使是最简单的二类网络，三元组也不能同时涉及来自网络不同部分的正样本和负样本。

为了解决基于三元组的度量学习的这种不兼容性，在本文中，我们提出了一种新的基于五元组的方法来学习二分异构网络中的节点表示。

具体来说，我们生成包含来自网络两个不同部分的正样本和负样本的五元组。我们制定了两个学习目标，以容纳基于五元组的学习样本，一个基于邻近度的损失，通过 sigmoid 概率对五元组中的关系进行建模，以及一个角度损失，可以更稳健地维持相似性结构。

此外，我们还通过在节点邻域周围使用一维卷积算子来参数化特征学习。

与八种方法相比，对两个下游任务的广泛实验证明了我们方法的有效性。