Unsupervised Domain-adaptive Hash for Networks

TL;DR

This paper introduces UDAH, an unsupervised domain-adaptive hashing method for networks that improves efficiency and effectiveness in tasks like link prediction and node classification across multiple domains.

Contribution

The paper presents a novel unsupervised domain-adaptive hashing approach for networks, incorporating four task-specific components to enhance cross-domain network analysis.

Findings

Outperforms state-of-the-art methods in multiple network tasks

Achieves better efficiency in retrieval and storage

Effective across diverse network datasets

Abstract

Abundant real-world data can be naturally represented by large-scale networks, which demands efficient and effective learning algorithms. At the same time, labels may only be available for some networks, which demands these algorithms to be able to adapt to unlabeled networks. Domain-adaptive hash learning has enjoyed considerable success in the computer vision community in many practical tasks due to its lower cost in both retrieval time and storage footprint. However, it has not been applied to multiple-domain networks. In this work, we bridge this gap by developing an unsupervised domain-adaptive hash learning method for networks, dubbed UDAH. Specifically, we develop four {task-specific yet correlated} components: (1) network structure preservation via a hard groupwise contrastive loss, (2) relaxation-free supervised hashing, (3) cross-domain intersected discriminators, and (4) semantic center alignment. We conduct a wide range of experiments to evaluate the effectiveness and efficiency of our method on a range of tasks including link prediction, node classification, and neighbor recommendation. Our evaluation results demonstrate that our model achieves better performance than the state-of-the-art conventional discrete embedding methods over all the tasks.