Embedding Dynamic Attributed Networks by Modeling the Evolution Processes

Proceedings of the 28th International Conference on Computational Linguistics, pages 6809–6819 Barcelona, Spain (Online), December 8-13, 2020 6809 Embedding Dynamic Attributed Networks by Modeling the Evolution Processes Zenan Xu1,2, Zijing Ou1, Qinliang Su1,2,3∗, Jianxing Yu1, Xiaojun Quan1 and Zhenkun Lin1,2 1School of Data and Computer Science, Sun Yat-sen University 2Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, China 3Key Lab. of Machine Intelligence and Advanced Computing, Ministry of Education, China {xuzn, ouzj, linzhk3}@mail2.sysu.edu.cn {suqliang, yujx, quanxj3}@mail.sysu.edu.cn Abstract Network embedding has recently emerged as a promising technique to embed nodes of a net- work into low-dimensional vectors. While fairly successful, most existing works focus on the embedding techniques for static networks. But in practice, there are many networks that are evolving over time and hence are dynamic, e.g., the social networks. To address this issue, a high-order spatio-temporal embedding model is developed to track the evolutions of dynamic networks. Specifically, an activeness-aware neighborhood embedding method is first proposed to extract the high-order neighborhood information at each given timestamp. Then, an embed- ding prediction framework is further developed to capture the temporal correlations, in which the attention mechanism is employed instead of recurrent neural networks (RNNs) for its efficiency in computing and flexibility in modeling. Extensive experiments are conducted on four real- world datasets from three different areas. It is shown that the proposed method outperforms all the baselines by a substantial margin for the tasks of dynamic link prediction and node classifi- cation, which demonstrates the effectiveness of the proposed methods on tracking the evolutions of dynamic networks. 1 Introduction Network embedding (NE) aims to represent each node by a low-dimensional vector, while seeking to preserve their neighborhood information as much as possible. It has been shown that working on the low- dimensional representations is much more efficient than on the original large-scale networks directly in various real-world applications, such as friend recommendation, product advertising, community detec- tion (Cavallari et al., 2017), nodes classification etc. Because of its capability in facilitating downstream applications, many methods have been developed to embed network nodes into vectors efficiently and ef- fectively, like DeepWalk in (Perozzi et al., 2014), LINE in (Tang et al., 2015), Node2Vec in (Grover and Leskovec, 2016) etc. Later, the attributes/texts available at nodes are further taken into account, e.g. the CANE in (Tu et al., 2017) and WANE in (Shen et al., 2018), to obtain more comprehensive embeddings. However, these methods mostly focus on static networks, but in practice, networks are often dynamic. In social networks, for instance, new friend connections are established all the time, and user profiles are also updated from time to time. For these dynamic networks, how to learn their embeddings, and more importantly, how to leverage the embeddings to predict their evolution trends is crucial for many applications. Existing methods for dynamic network embedding can be roughly divided into two categories. The first category concerns about how to obtain new embeddings from the stale ones efficiently when changes of networks are observed. In …

Content truncated to 500 words