Neural Embedding Propagation on Heterogeneous Networks
This work addresses the limitation of label propagation in handling heterogeneous networks, which is a problem for researchers and practitioners in network analysis and semi-supervised learning, representing an incremental advancement.
The paper tackles the problem of label scarcity in semi-supervised learning by proposing neural embedding propagation (NEP) for heterogeneous networks, which accommodates multi-typed objects and links, and demonstrates its effectiveness, efficiency, and robustness on three datasets compared to state-of-the-art methods.
Classification is one of the most important problems in machine learning. To address label scarcity, semi-supervised learning (SSL) has been intensively studied over the past two decades, which mainly leverages data affinity modeled by networks. Label propagation (LP), however, as the most popular SSL technique, mostly only works on homogeneous networks with single-typed simple interactions. In this work, we focus on the more general and powerful heterogeneous networks, which accommodate multi-typed objects and links, and thus endure multi-typed complex interactions. Specifically, we propose \textit{neural embedding propagation} (NEP), which leverages distributed embeddings to represent objects and dynamically composed modular networks to model their complex interactions. While generalizing LP as a simple instance, NEP is far more powerful in its natural awareness of different types of objects and links, and the ability to automatically capture their important interaction patterns. Further, we develop a series of efficient training strategies for NEP, leading to its easy deployment on real-world heterogeneous networks with millions of objects. With extensive experiments on three datasets, we comprehensively demonstrate the effectiveness, efficiency, and robustness of NEP compared with state-of-the-art network embedding and SSL algorithms.