Autoencoder-based unsupervised clustering and hashing

Abstract

Faced with a large amount of data and high-dimensional data information in a database, the existing exact nearest neighbor retrieval methods cannot obtain ideal retrieval results within an acceptable retrieval time. Therefore, researchers have begun to focus on approximate nearest neighbor retrieval. Recently, the hashing-based approximate nearest neighbor retrieval method has attracted increasing attention because of its small storage space and high retrieval efficiency. The development of neural networks has also promoted progress in hash learning. However, these methods are mostly supervised. In practical applications, annotating large amounts of data is a very time-consuming and laborious task. Furthermore, efficiently using a large amount of unlabeled data for hash learning is challenging. In this paper, we create a new autoencoder variant to efficiently capture the features of high-dimensional data, and propose an unsupervised deep hashing method for large-scale data retrieval, named as Autoencoder-based Unsupervised Clustering and Hashing (AUCH). By constructing a hashing layer as a hidden layer of the autoencoder, hash learning is performed together with unsupervised clustering by minimizing the overall loss. AUCH can unify unsupervised clustering and retrieval tasks into a single learning model. In addition, the method can use a deep neural network to simultaneously learn feature representations, hashing functions and cluster assignments. Experimental results on standard datasets indicate that AUCH achieves competitive results compared to state-of-the-art models for retrieval and clustering tasks.

Graph Convolutional Network Combined with Semantic Feature Guidance for Deep Clustering

“…Finally, a major breakthrough was made in clustering with the characteristics obtained through the adversarial loss constraint encoder and discrimination algorithm. In 2021, Zhang and Qian [7] proposed an unsupervised deep hashing method for large-scale data retrieval called autoencoder-based unsupervised clustering and hashing (AUCH). AUCH can unify unsupervised clustering and retrieval tasks into a single learning model.…”

“…(3) deep clustering via joint convolutional autoencoder [12] 0.392 0.315 0.206 0.210 0.400 0.219 0.350 0.3864 DEC [13] 0.843 0.441 0.244 0.359 0.460 0.257 0.426 0.4540 DEPICT [18] 0.917 0.964 0.212 0.224 0.455 0.243 0.324 0.4130 DAC [41] 0.977 0.653 0.521 0.469 0.307 0.236 0.312 0.3250 Deepcluster [14] --0.376 0.332 ----IIC [8] 0.992 -0.617 0.596 ----DCCS [6] 0.989 -0.656 0.536 ----AUCH [7] 0.960 0.775 0.318 0.734 ----GFDC 0.993 0.974 0.615 0.720 0.902 0.833 0.993 0.9520 Note: "**" denotes the clustering accuracy provided by a previous study, "-" denotes no value available, and the best results are emphasized in bold.…”

“…As reported in Refs. [6,7], an evident gap exists between the experimental performance of unsupervised clustering and supervised classification. Furthermore, invariant information clustering (IIC) [8] , a state-of-theart deep clustering method, yields an unsupervised clustering accuracy of 0.596 and a semisupervised clustering accuracy of 0.888 on the STL-10 dataset.…”

Meta-Parameter Selection for Embedding Generation of Latency Spaces in Auto Encoder Analytics

“…The idea of autoencoders exists for more than 30 years [6] and the applications are presently widespread. They range from generalization to classification tasks, denoising, anomaly detection, recommender systems, clustering and dimensionality reduction with stunning results [7,[9][10][11][12][13]. Within this work, we focus on the latter two use cases, wherein autoencoders perform unsupervised feature extraction and dimensionality reduction [14,15].…”