The rapid development of the Industrial Internet of Things (IIoT) has enabled the communication of numerous devices, resulting in the generation of massive time-series data. The goal of time-series anomaly detection a...
详细信息
Cumulative experimental studies have demonstrated the critical roles of microRNAs (miRNAs) in the diverse fundamental and important biological processes, and in the development of numerous complex human diseases. Thus...
详细信息
Cumulative experimental studies have demonstrated the critical roles of microRNAs (miRNAs) in the diverse fundamental and important biological processes, and in the development of numerous complex human diseases. Thus, exploring the relationships between miRNAs and diseases is helpful with understanding the mechanisms, the detection, diagnosis, and treatment of complex diseases. As the identification of miRNA-disease associations via traditional biological experiments is time-consuming and expensive, an effective computational prediction method is appealing. In this study, we present a deep learning framework with variational graph auto-encoder for miRNA-disease association prediction (VGAE-MDA). VGAE-MDA first gets the representations of miRNAs and diseases from the heterogeneous networks constructed by miRNA-miRNA similarity, disease-disease similarity, and known miRNA-disease associations. Then, VGAE-MDA constructs two sub-networks: miRNA-based network and disease-based network. Combining the representations based on the heterogeneous network, two variational graph auto-encoders (VGAE) are deployed for calculating the miRNA-disease association scores from two subnetworks, respectively. Lastly, VGAE-MDA obtains the final predicted association score for a miRNA-disease pair by integrating the scores from these two trained networks. Unlike the previous model, the VGAE-MDA can mitigate the effect of noises from random selection of negative samples. Besides, the use of graph convolutional neural (GCN) network can naturally incorporate the node features from the graph structure while the variational autoencoder (VAE) makes use of latent variables to predict associations from the perspective of data distribution. The experimental results show that VGAE-MDA outperforms the state-of-the-art approaches in miRNA-disease association prediction. Besides, the effectiveness of our model has been further demonstrated by case studies.
Learned image compression techniques have achieved considerable development in recent years. In this paper, we find that the performance bottleneck lies in the use of a single hyperprior decoder, in which case the ter...
详细信息
Learned image compression techniques have achieved considerable development in recent years. In this paper, we find that the performance bottleneck lies in the use of a single hyperprior decoder, in which case the ternary Gaussian model collapses to a binary one. To solve this, we propose to use three hyperprior decoders to separate the decoding process of the mixed parameters in discrete Gaussian mixture likelihoods, achieving more accurate parameters estimation. Experimental results demonstrate the proposed method optimized by MS-SSIM achieves on average 3.36% BD-rate reduction compared with state-of-the-art approach. The contribution of the proposed method to the coding time and FLOPs is negligible.
To better control eutrophication, reliable and accurate information on phosphorus and nitrogen loading is desired. However, the high-frequency monitoring of these variables is economically impractical. This necessitat...
详细信息
To better control eutrophication, reliable and accurate information on phosphorus and nitrogen loading is desired. However, the high-frequency monitoring of these variables is economically impractical. This necessitates using virtual sensing to predict them by utilizing easily measurable variables as inputs. While the predictive performance of these data-driven, virtual-sensor models depends on the use of adequate training samples (in quality and quantity), the procurement and operational cost of nitrogen and phosphorus sensors make it impractical to acquire sufficient samples. For this reason, the variational autoencoder, which is one of the most prominent methods in generative models, was utilized in the present work for generating synthetic data. The generation capacity of the model was verified using water-quality data from two tributaries of the River Thames in the United Kingdom. Compared to the current state of the art, our novel data augmentation-including proper experimental settings or hyperparameter optimization-improved the root mean squared errors by 23-63%, with the most significant improvements observed when up to three predictors were used. In comparing the predictive algorithms' performances (in terms of the predictive accuracy and computational cost), k-nearest neighbors and extremely randomized trees were the best-performing algorithms on average.
Designing realistic digital humans is extremely complex. Most data-driven generative models used to simplify the creation of their underlying geometric shape do not offer control over the generation of local shape att...
详细信息
Designing realistic digital humans is extremely complex. Most data-driven generative models used to simplify the creation of their underlying geometric shape do not offer control over the generation of local shape attributes. In this paper, we overcome this limitation by introducing a novel loss function grounded in spectral geometry and applicable to different neural-network-based generative models of 3D head and body meshes. Encouraging the latent variables of mesh variational autoencoders (VAEs) or generative adversarial networks (GANs) to follow the local eigenprojections of identity attributes, we improve latent disentanglement and properly decouple the attribute creation. Experimental results show that our local eigenprojection disentangled (LED) models not only offer improved disentanglement with respect to the state-of-the-art, but also maintain good generation capabilities with training times comparable to the vanilla implementations of the models. Our code and pre-trained models are available at .
Typically, hierarchical reinforcement learning (RL) requires skills that are applicable to various downstream tasks. Although several recent studies have proposed the supervised and unsupervised learning of such skill...
详细信息
Typically, hierarchical reinforcement learning (RL) requires skills that are applicable to various downstream tasks. Although several recent studies have proposed the supervised and unsupervised learning of such skills, the learned skills are often entangled, which hinders their interpretation. To alleviate this, we propose a novel method to use weak labels for learning disentangled skills from the continuous latent representations of trajectories. To this end, we extended a trajectory variational autoencoder (VAE) to impose an inductive bias using weak labels, which explicitly enforces the disentangling of the trajectory representations into factors of interest intended for the model to learn. Using the latent representations as skills, a skill-based policy network is trained to generate trajectories similar to the learned decoder of the trajectory VAE. Furthermore, using the disentangled skill, we propose a skill repetition that can expand the entire trajectories generated by the policy at test time, resulting in an effective planning strategy. Experiments were performed on several challenging navigation tasks in mazes, and the results demonstrate the effectiveness of our method at solving hierarchical RL problems even with a long horizon and sparse rewards.
Deep neural networks have become increasingly important in recent years for creating molecules with desirable properties. In general, SMILES strings are used to train deep neural network based models. The trained mode...
详细信息
Deep neural networks have become increasingly important in recent years for creating molecules with desirable properties. In general, SMILES strings are used to train deep neural network based models. The trained model is then used to generate the desired molecules. Unfortunately, due to syntactical and semantic flaws in the representation, the SMILES string generates a substantial number of invalid molecules. SMILES representation fails to efficiently handle rings, branch and bonds between atoms. Lack of robustness in dealing with the cited aspects results in abundance of invalid strings. To overcome this limitation, this paper proposes a SMILES like representation, called GenSMILES. GenSMILES tackles syntactical and semantic issues by relying upon derivative rules to apply constraints. This causes a generative model produces more valid SMILES strings. By substituting a single notation for the pair representation of branches and rings in SMILES with a ) and boolean AND, respectively, GenSMILES corrects the syntactical issues. The mismatching of atom's bonds is the main cause of semantic errors. GenSMILES addresses such issues by employing derivation rules during string conversion from GenSMILES to SMILES. Every SMILES string can be represented with an equivalent GenSMILES. When used for designing drug molecule, GenSMILES increases molecule's validity when compared with SMILES and DeepSMILES on two popular architectures i.e., Recurrent Neural Network and variational autoencoder. The main benefit of GenSMILES is that it can be applied directly to generative algorithms without adapting the model environment. GenSMILES is beneficial not only to generative approaches of DL but also to the approaches that use SMILES string-like representation. On most of the datasets, GenSMILES is effective in improving validity above 90% and diversity score 15. GenSMILES results in more diversity in the properties of generated molecules and allows exploration of larger portion of undisc
Parametric Modeling, Generative Design, and Performance-Based Design have gained increasing attention in the AEC field as a way to create a wide range of design variants while focusing on performance attributes rather...
详细信息
Parametric Modeling, Generative Design, and Performance-Based Design have gained increasing attention in the AEC field as a way to create a wide range of design variants while focusing on performance attributes rather than building codes. However, the relationships between design parameters and performance attributes are often very complex, resulting in a highly iterative and unguided process. In this paper, we argue that a more goal-oriented design process is enabled by an inverse formulation that starts with performance attributes instead of design parameters. A Deep Conditional Generative Design workflow is proposed that takes a set of performance attributes and partially defined design features as input and produces a complete set of design parameters as output. A model architecture based on a Conditional variational autoencoder is presented along with different approximate posteriors, and evaluated on four different case studies. Compared to Genetic Algorithms, our method proves superior when utilizing a pre-trained model.
With the gradual integration of internet technology and the industrial control field, industrial control systems (ICSs) have begun to access public networks on a large scale. Attackers use these public network interfa...
详细信息
With the gradual integration of internet technology and the industrial control field, industrial control systems (ICSs) have begun to access public networks on a large scale. Attackers use these public network interfaces to launch frequent invasions of industrial control systems, thus resulting in equipment failure and downtime, production data leakage, and other serious harm. To ensure security, ICSs urgently need a mature intrusion detection mechanism. Most of the existing research on intrusion detection in ICSs focuses on improving the accuracy of intrusion detection, thereby ignoring the problem of limited equipment resources in industrial control environments, which makes it difficult to apply excellent intrusion detection algorithms in practice. In this study, we first use the spectral residual (SR) algorithm to process the data;we then propose the improved lightweight variational autoencoder (LVA) with autoregression to reconstruct the data, and we finally perform anomaly determination based on the permutation entropy (PE) algorithm. We construct a lightweight unsupervised intrusion detection model named LVA-SP. The model as a whole adopts a lightweight design with a simpler network structure and fewer parameters, which achieves a balance between the detection accuracy and the system resource overhead. Experimental results on the ICSs dataset show that our proposed LVA-SP model achieved an F1-score of 84.81% and has advantages in terms of time and memory overhead.
Recently, network architecture search is gaining popularity. The neural network representation as a directed acyclic graph is considered for subsequent architecture optimization. Currently, most of the existing encode...
详细信息
Recently, network architecture search is gaining popularity. The neural network representation as a directed acyclic graph is considered for subsequent architecture optimization. Currently, most of the existing encoders rely only on the model layer properties and do not take into account the attributes of layers. This work proposes an algorithm for mapping a CNN network to a vector space considering the layer attributes, such as different dimensions of a particular layer. The proposed algorithm was compared with D-VAE and DVAE-EMB and showed less information loss caused by the mapping of a network to a vector space. As the results show, the performance of the model was shown after direct conversion to embedding and reverse conversion to architecture. The method allows more accurate neural network architecture mapping into a vector form, which will improve the search for the best architecture. The method implementation is publicly available at https://***/Turukmokto/GraphEmbedding-dev .
暂无评论