MANELA: A Multi-Agent Algorithm for Learning Network Embeddings

TL;DR

This paper introduces MANELA, a multi-agent algorithm for learning network embeddings suitable for distributively stored networks, overcoming the limitations of centralized methods and demonstrating advantages through theoretical and experimental analysis.

Contribution

The paper proposes a novel multi-agent model and algorithm, MANELA, for distributed network embedding learning, addressing a gap in existing centralized approaches.

Findings

MANELA outperforms centralized algorithms in experiments.

Theoretical analysis confirms MANELA's advantages.

Visualization links MANELA to DeepWalk.

Abstract

Playing an essential role in data mining, machine learning has a long history of being applied to networks on multifarious tasks and has played an essential role in data mining. However, the discrete and sparse natures of networks often render it difficult to apply machine learning directly to networks. To circumvent this difficulty, one major school of thought to approach networks using machine learning is via network embeddings. On the one hand, this network embeddings have achieved huge success on aggregated network data in recent years. On the other hand, learning network embeddings on distributively stored networks still remained understudied: To the best of our knowledge, all existing algorithms for learning network embeddings have hitherto been exclusively centralized and thus cannot be applied to these networks. To accommodate distributively stored networks, in this paper, we proposed a multi-agent model. Under this model, we developed the multi-agent network embedding learning algorithm (MANELA) for learning network embeddings. We demonstrate MANELA's advantages over other existing centralized network embedding learning algorithms both theoretically and experimentally. Finally, we further our understanding in MANELA via visualization and exploration of its relationship to DeepWalk.