Feature Hashing for Network Representation Learning

Feature Hashing for Network Representation Learning

Qixiang Wang, Shanfeng Wang, Maoguo Gong, Yue Wu

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 2812-2818. https://doi.org/10.24963/ijcai.2018/390

The goal of network representation learning is to embed nodes so as to encode the proximity structures of a graph into a continuous low-dimensional feature space. In this paper, we propose a novel algorithm called node2hash based on feature hashing for generating node embeddings. This approach follows the encoder-decoder framework. There are two main mapping functions in this framework. The first is an encoder to map each node into high-dimensional vectors. The second is a decoder to hash these vectors into a lower dimensional feature space. More specifically, we firstly derive a proximity measurement called expected distance as target which combines position distribution and co-occurrence statistics of nodes over random walks so as to build a proximity matrix, then introduce a set of T different hash functions into feature hashing to generate uniformly distributed vector representations of nodes from the proximity matrix. Compared with the existing state-of-the-art network representation learning approaches, node2hash shows a competitive performance on multi-class node classification and link prediction tasks on three real-world networks from various domains.
Keywords:
Machine Learning: Data Mining
Multidisciplinary Topics and Applications: Social Sciences
Machine Learning: Deep Learning
Machine Learning Applications: Networks