论文标题
链接预测的无参数动态图嵌入
Parameter-free Dynamic Graph Embedding for Link Prediction
论文作者
论文摘要
动态交互图已被广泛采用，以建模用户 - 项目交互的演变。在对用户偏好建模以在动态交互图中进行链接预测的偏好时，有两个关键因素：1）用户之间的协作关系和2）用户个性化的交互模式。现有方法通常会隐式考虑这两个因素，这可能会导致两个因素分歧时嘈杂的用户建模。此外，它们通常需要使用后传播的耗时的参数学习，这对于实时用户偏好建模而言是令人难以置信的。为此，本文提出了FreeGem，这是一种用于链接预测的无参数动态图嵌入方法。 Firstly, to take advantage of the collaborative relationships, we propose an incremental graph embedding engine to obtain user/item embeddings, which is an Online-Monitor-Offline architecture consisting of an Online module to approximately embed users/items over time, a Monitor module to estimate the approximation error in real time and an Offline module to calibrate the user/item embeddings when the online approximation errors exceed a threshold.同时，我们将属性信息集成到模型中，这使FreeGem能够更好地建模属于某些不足的组的用户。其次，我们设计了一个个性化的动态交互模式模块，该模型将动态时间衰减与注意机制结合起来，以建模用户短期兴趣。两个链接预测任务上的实验结果表明，FreeGem可以在准确性方面胜过最先进的方法，同时效率提高了36倍。所有代码和数据集都可以在https://github.com/fudancisl/freegem中找到。
Dynamic interaction graphs have been widely adopted to model the evolution of user-item interactions over time. There are two crucial factors when modelling user preferences for link prediction in dynamic interaction graphs: 1) collaborative relationship among users and 2) user personalized interaction patterns. Existing methods often implicitly consider these two factors together, which may lead to noisy user modelling when the two factors diverge. In addition, they usually require time-consuming parameter learning with back-propagation, which is prohibitive for real-time user preference modelling. To this end, this paper proposes FreeGEM, a parameter-free dynamic graph embedding method for link prediction. Firstly, to take advantage of the collaborative relationships, we propose an incremental graph embedding engine to obtain user/item embeddings, which is an Online-Monitor-Offline architecture consisting of an Online module to approximately embed users/items over time, a Monitor module to estimate the approximation error in real time and an Offline module to calibrate the user/item embeddings when the online approximation errors exceed a threshold. Meanwhile, we integrate attribute information into the model, which enables FreeGEM to better model users belonging to some under represented groups. Secondly, we design a personalized dynamic interaction pattern modeller, which combines dynamic time decay with attention mechanism to model user short-term interests. Experimental results on two link prediction tasks show that FreeGEM can outperform the state-of-the-art methods in accuracy while achieving over 36X improvement in efficiency. All code and datasets can be found in https://github.com/FudanCISL/FreeGEM.
