MLANE: Meta-Learning Based Adaptive Network Embedding

TL;DR

MLANE is a novel meta-learning based approach that adaptively learns network embeddings by balancing homophily and structural equivalence, improving performance across various tasks.

Contribution

MLANE introduces an end-to-end meta-learning framework for adaptive network embedding that dynamically balances homophily and structural equivalence.

Findings

Significant performance improvements over baselines

Effective adaptive sampling strategy learning

Validated on real datasets

Abstract

Most existing random walk based network embedding methods often follow only one of two principles, homophily or structural equivalence. In real world networks, however, nodes exhibit a mixture of homophily and structural equivalence, which requires adaptive network embedding that can adaptively preserve both homophily and structural equivalence for different nodes in different down-stream analysis tasks. In this paper, we propose a novel method called Meta-Learning based Adaptive Network Embedding (MLANE), which can learn adaptive sampling strategy for different nodes in different tasks by incorporating sampling strategy learning with embedding learning into one optimization problem that can be solved via an end-to-end meta-learning framework. In extensive experiments on real datasets, MLANE shows significant performance improvements over the baselines. The source code of MLANE and the datasets used in experiments and all the hyperparameter settings for baselines are available at https://github.com/7733com/MLANE.