Search

Hashing is an efficient method for nearest neighbor search in large-scale data space by embedding high-dimensional feature descriptors into a similarity preserving Hamming space with a low dimension. However, large-scale high-speed retrieval through binary code has a certain degree of reduction in retrieval accuracy compared to traditional retrieval methods. We have noticed that multi-view methods can well preserve the diverse characteristics of data. Therefore, we try to introduce the multi-view deep neural network into the hash learning field, and design an efficient and innovative retrieval model, which has achieved a significant improvement in retrieval performance. In this paper, we propose a supervised multi-view hash model which can enhance the multi-view information through neural networks. This is a completely new hash learning method that combines multi-view and deep learning methods. The proposed method utilizes an effective view stability evaluation method to actively explore the relationship among views, which will affect the optimization direction of the entire network. We have also designed a variety of multi-data fusion methods in the Hamming space to preserve the advantages of both convolution and multi-view. In order to avoid excessive computing resources on the enhancement procedure during retrieval, we set up a separate structure called memory network which participates in training together. The proposed method is systematically evaluated on the CIFAR-10, NUS-WIDE and MS-COCO datasets, and the results show that our method significantly outperforms the state-of-the-art single-view and multi-view hashing methods.

Network pruning offers an opportunity to facilitate deploying convolutional neural networks (CNNs) on resource-limited embedded devices. Pruning more redundant network structures while ensuring network accuracy is challenging. Most existing CNN compression methods iteratively prune the “least important” filters and retrain the pruned network layer-by-layer, which may lead to a sub-optimal solution. In this paper, an end-to-end structured network pruning method based on adversarial multi-indicator architecture selection (AMAS) is presented. The pruning is implemented by striving to align the output of the baseline network with the output of the pruned network in a generative adversarial framework. Furthermore, to efficiently find optimal pruned architecture under constrained resources, an adversarial fine-tuning network selection strategy is designed, in which two contradictory indicators, namely pruned channel number and network classification accuracy, are considered. Experiments on SVHN show that AMAS reduces 75.37% of FLOPs and 74.42% of parameters with even 0.36% accuracy improvement for ResNet-110. On CIFAR-10, it achieves a reduction of 77.08% FLOPs and removes 73.98% of parameters with negligible accuracy cost for GoogLeNet. In particular, it obtains a 56.87% pruned rate in FLOPs and 59.18% parameters reduction, while with an increase of 0.49% accuracy for ResNet-110, which significantly outperforms state-of-the-art methods.

Emotion recognition by physiological signals is an effective way to discern the inner state of human beings and therefore has been widely adopted in many user-centered applications. The majority of current state-of-the-art methods focus on exploring relationship among emotion and physiological signals. Given some particular features of the natural process of emotional expression, it is still a challenging and urgent issue to efficiently combine such high-order correlations among multimodal physiological signals and subjects. To tackle the problem, a novel multi-hypergraph neural networks is proposed, in which one hypergraph is established with one type of physiological signals to formulate inter-subject correlations. Each one of the vertices in a hypergraph stands for one subject with a description of its related stimuli, and the complex correlations among the vertices can be formulated through hyperedges. With the multi-hypergraph structure of the subjects, emotion recognition is translated into classification of vertices in the multi-hypergraph structure. Experimental results with the DEAP dataset and ASCERTAIN dataset demonstrate that the proposed method outperforms the current state-of-the-art methods.

Satellite image classification is a challenging task if the input labels are not sufficiently accurate. The automatic cloud cover assessment (ACCA), for example, aims to classify the cloud covers of satellite images as alphabetical categories from A to E showing the escalating levels of clouds; however, those labels for training are often obtained by a subjective qualitative assessment, i.e., they may be not accurate. Therefore, this paper studies how to conduct ACCA under this circumstance. We propose a label smoothing approach and improve the accuracy around 3 percentage points (e.g., from 75.9% to 78.4% for ResNet network) without changing other network structures and parameters.

This paper studies a multi-Unmanned Aerial Vehicles (UAVs) -enabled wireless powered communication network (WPCN). We present a novel use of UAVs with energy harvesting module. Thus, UAVs are used as flying base stations to collecting data and charging ground IoT devices via radio frequency (RF). Due to energy constraint and limited coverage of single UAV, its applications are limited. So we investigate a Multi-UAVs solution to enhance system transmitting performance via UAVs' cooperation. In particular, we focus on finding a tradeoff solution to prolong devices lifetime and improve the average uplink throughput efficiency among all ground users in a given time. To tackle this problem, we first consider a relaxed problem in which IoT devices are distributed in different residential blocks. A Work-Gain algorithm is designed for the relaxed problem. The performances comparison are presented in numerical results. Our performance analysis and simulation results have demonstrated that the proposed approach can improve the uplink performance approximately by 20% compared to other methods in certain circumstances.

Over the past decade, increasing research efforts have been concentrated on emotion recognition from physiological signals due to their capability on emotion information representation. Existing works mainly focus on exploring the relationship between stimulus and subjects, while ignoring the effects of latent correlations among different subjects, which are important for personalized emotion recognition. To tackle this issue, we aim to conduct emotion recognition using multi-modal physiological signals through an edge-weighted hyper-graph neural network, in which complex relationship among subjects is formulated using hypergraph for each modality respectively. In our model, the differences in significance of influence which various samples leave on the classification can be better represented. The major contribution of this network lies in its concern that the associate strengths between various samples are different, which have different impact on the training result. The hyperedge between the vertices with closer correlation should be assigned a larger weight. Reversely, the looser relation, the minor weight. To evaluate the proposed method, experiments have been conducted on the DEAP dataset and ASCERTAIN dataset. Experimental results and comparison with state-of-the-art methods show that the proposed method can achieve better performance.

In recent years, graph/hypergraph-based deep learning methods have attracted much attention from researchers. These deep learning methods take graph/hypergraph structure as prior knowledge in the model. However, hidden and important relations are not directly represented in the inherent structure. To tackle this issue, we propose a dynamic hypergraph neural networks framework (DHGNN), which is composed of the stacked layers of two modules: dynamic hypergraph construction (DHG) and hypergrpah convolution (HGC). Considering initially constructed hypergraph is probably not a suitable representation for data, the DHG module dynamically updates hypergraph structure on each layer. Then hypergraph convolution is introduced to encode high-order data relations in a hypergraph structure. The HGC module includes two phases: vertex convolution and hyperedge convolution, which are designed to aggregate feature among vertices and hyperedges, respectively. We have evaluated our method on standard datasets, the Cora citation network and Microblog dataset. Our method outperforms state-of-the-art methods. More experiments are conducted to demonstrate the effectiveness and robustness of our method to diverse data distributions.

Link prediction aims at inferring missing links or predicting future ones based on the currently observed network. This topic is important for many applications such as social media, bioinformatics and recommendation systems. Most existing methods focus on homogeneous settings and consider only low-order pairwise relations while ignoring either the heterogeneity or high-order complex relations among different types of nodes, which tends to lead to a sub-optimal embedding result. This paper presents a method named Heterogeneous Hypergraph Variational Autoencoder (HeteHG-VAE) for link prediction in heterogeneous information networks (HINs). It first maps a conventional HIN to a heterogeneous hypergraph with a certain kind of semantics to capture both the high-order semantics and complex relations among nodes, while preserving the low-order pairwise topology information of the original HIN. Then, deep latent representations of nodes and hyperedges are learned by a Bayesian deep generative framework from the heterogeneous hypergraph in an unsupervised manner. Moreover, a hyperedge attention module is designed to learn the importance of different types of nodes in each hyperedge. The major merit of HeteHG-VAE lies in its ability of modeling multi-level relations in heterogeneous settings. Extensive experiments on real-world datasets demonstrate the effectiveness and efficiency of the proposed method.