MLANE: Meta-Learning Based Adaptive Network Embedding

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.

References in corpus (7)

• Efficient Estimation of Word Representations in Vector Space
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• struc2vec: Learning Node Representations from Structural Identity
• A Simple Neural Attentive Meta-Learner
• Role Discovery in Networks
• On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning
• RiWalk: Fast Structural Node Embedding via Role Identification