Unsupervised Domain-adaptive Hash for Networks
This work addresses the need for efficient and adaptive learning algorithms for large-scale networks where labels may be unavailable, representing an incremental advancement by extending domain-adaptive hashing from computer vision to network domains.
The paper tackled the problem of applying domain-adaptive hash learning to multiple-domain networks, which had not been done before, and developed an unsupervised method called UDAH that achieved better performance than state-of-the-art conventional discrete embedding methods across tasks like link prediction, node classification, and neighbor recommendation.
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.