Discrete Embedding for Latent Networks

Abstract

<jats:p>Discrete network embedding emerged recently as a new direction of network representation learning. Compared with traditional network embedding models, discrete network embedding aims to compress model size and accelerate model inference by learning a set of short binary codes for network vertices. However, existing discrete network embedding methods usually assume that the network structures (e.g., edge weights) are readily available. In real-world scenarios such as social networks, sometimes it is impossible to collect explicit network structure information and it usually needs to be inferred from implicit data such as information cascades in the networks. To address this issue, we present an end-to-end discrete network embedding model for latent networks DELN that can learn binary representations from underlying information cascades. The essential idea is to infer a latent Weisfeiler-Lehman proximity matrix that captures node dependence based on information cascades and then to factorize the latent Weisfiler-Lehman matrix under the binary node representation constraint. Since the learning problem is a mixed integer optimization problem, an efficient maximal likelihood estimation based cyclic coordinate descent (MLE-CCD) algorithm is used as the solution. Experiments on real-world datasets show that the proposed model outperforms the state-of-the-art network embedding methods.</jats:p>

Attributed Network Embedding Using an Improved Weisfeiler-Lehman Schema and a Novel Deep Skip-Gram

“…Neighborhood aggregation algorithms are based on the principle that each vertex receives messages from its neighbors and uses them to update its representation [44]. H. Yang et al [16,45] introduced the concept of a Weisfeiler-Lehman matrix to capture the interplay between a node's structure and its attributes. Xuewei Ma et.al.…”

Unsupervised Domain-adaptive Hash for Networks

“…• Discrete Embedding for Latent Networks (DELN) [16] is an end-to-end discrete network embedding method to learn binary representations.…”

“…However, the tanh function could produce undesirable relaxation errors [10] and degrade the quality of learned hash codes. Although some works [3,16] have proposed to leverage an alternating algorithm to optimize hash codes, it is hard to integrate it into a deep neural network in an end-to-end fashion.…”