# Unsupervised Domain-adaptive Hash for Networks

arXiv: https://arxiv.org/abs/2108.09136 · HTML: https://mlsanity.com/paper/2108.09136/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 50 references that are in the map.
- First posted on arXiv 20 Aug 2021.

## Builds on (most cited first, 24 of 24)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?](https://mlsanity.com/paper/1706.00712/) (2017)
- [Simultaneous Deep Transfer Across Domains and Tasks](https://mlsanity.com/paper/1510.02192/) (2015)
- [Graph Embedding Techniques, Applications, and Performance: A Survey](https://mlsanity.com/paper/1705.02801/) (2017)
- [HashNet: Deep Learning to Hash by Continuation](https://mlsanity.com/paper/1702.00758/) (2017)
- [A Survey on Learning to Hash](https://mlsanity.com/paper/1606.00185/) (2016)
- [Network Representation Learning: A Survey](https://mlsanity.com/paper/1801.05852/) (2017)
- [Adversarially Regularized Graph Autoencoder for Graph Embedding](https://mlsanity.com/paper/1802.04407/) (2018)
- [Unsupervised Domain Adaptive Re-Identification: Theory and Practice](https://mlsanity.com/paper/1807.11334/) (2018)
- [Deep Cross-Modal Hashing](https://mlsanity.com/paper/1602.02255/) (2016)
- [Differentiable Product Quantization for End-to-End Embedding Compression](https://mlsanity.com/paper/1908.09756/) (2019)
- [Compressing Word Embeddings via Deep Compositional Code Learning](https://mlsanity.com/paper/1711.01068/) (2017)
- [Deep Supervised Hashing with Triplet Labels](https://mlsanity.com/paper/1612.03900/) (2016)
- [Binary Generative Adversarial Networks for Image Retrieval](https://mlsanity.com/paper/1708.04150/) (2017)
- [Learning to Hash with Binary Deep Neural Network](https://mlsanity.com/paper/1607.05140/) (2016)
- [Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval](https://mlsanity.com/paper/1807.04629/) (2018)
- [Hashing with binary autoencoders](https://mlsanity.com/paper/1501.00756/) (2015)
- [Deep Discrete Hashing with Self-supervised Pairwise Labels](https://mlsanity.com/paper/1707.02112/) (2017)
- [Multi-Prototype Networks for Unconstrained Set-based Face Recognition](https://mlsanity.com/paper/1902.04755/) (2019)
- [HashGAN:Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval](https://mlsanity.com/paper/1711.09347/) (2017)

## Abstract (arXiv)

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.